Production and energy system based on new energy-powered submerged arc furnace, and related control method

Abstract

The present invention relates to a production and energy system based on a new energy-powered submerged arc furnace, and a related control method. The production and energy system comprises a power transmission and distribution system, a renewable energy power generation system, an energy storage system, and a submerged arc furnace-based production system. The power transmission and distribution system is respectively connected to the renewable energy power generation system, the energy storage system, and the submerged arc furnace-based production system. The production and energy system further comprises an energy control system. The energy control system comprises: an integrated regulation and control system used for performing integrated regulation and control on the production and energy system by means of the power transmission and distribution system; a renewable energy power generation control system used for controlling operation of the renewable energy power generation system; an energy storage control system used for controlling operation of the energy storage system; and a submerged arc furnace-based production control system used for controlling operation of the submerged arc furnace-based production system. Compared with the prior art, the present invention has the advantages of optimizing energy utilization, achieving environmental protection and low-carbon development, improving the stability and reliability of the energy system, etc.

Description

Submerged arc furnace production and energy system based on new energy power supply and related control methods Technical Field

[0001] The present invention relates to the technical field of energy systems, and in particular to a submerged arc furnace production and energy system based on renewable energy power supply and related control methods. Background Art

[0002] Against the backdrop of promoting green, environmentally friendly, and low-carbon development, renewable energy is increasingly contributing to the energy system. However, submerged arc furnace loads present numerous challenges within this energy system. First, the energy utilization efficiency of submerged arc furnace loads is relatively low, resulting in energy waste. Second, the power of submerged arc furnace loads fluctuates significantly, leading to instability and unreliability in the energy system. Furthermore, a high proportion of renewable energy power supply presents several challenges. The intermittent nature of renewable energy power generation results in uncertainty in output power, posing challenges to balancing supply and demand in the energy system. Furthermore, centralized renewable energy power supply also presents challenges such as transmission losses and transmission line capacity limitations. Therefore, the implementation of an energy system combining submerged arc furnace loads with a high proportion of renewable energy power supply faces the challenges of improving the energy utilization efficiency of the submerged arc furnace loads and addressing issues such as fluctuating power levels and intermittent renewable energy power supply.

[0003] Summary of the Invention

[0004] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and to provide a submerged arc furnace production and energy system based on new energy power supply and related control methods.

[0005] The purpose of the present invention can be achieved by the following technical solutions:

[0006] A submerged arc furnace production and energy system based on new energy power supply includes a power transmission and distribution system, a renewable energy power generation system, an energy storage system and a submerged arc furnace production system, wherein the power transmission and distribution system is connected to the renewable energy power generation system, the energy storage system and the submerged arc furnace production system respectively.

[0007] Furthermore, the submerged arc furnace production and energy system also includes an energy control system, which includes:

[0008] An integrated control system for integrated control of the submerged arc furnace production and energy system through the power transmission and distribution system;

[0009] A renewable energy power generation control system, used to control the operation of the renewable energy power generation system;

[0010] An energy storage control system, used to control the operation of the energy storage system;

[0011] The submerged arc furnace production control system is used to control the operation of the submerged arc furnace production system.

[0012] Furthermore, the submerged arc furnace production and energy system further includes an exhaust gas recycling system, which is connected to the submerged arc furnace production system and the power transmission and distribution system respectively;

[0013] The energy control system also includes an exhaust gas recycling control system, which is used to control the operation of the exhaust gas recycling system.

[0014] Furthermore, the submerged arc furnace production and energy system further includes an external power grid connected to the power transmission and distribution system;

[0015] The energy control system further includes a power grid dispatching system, which is used to dispatch energy to an external power grid.

[0016] A method for controlling a submerged arc furnace production and energy system based on renewable energy power supply as described above comprises the following steps:

[0017] Establishing a mathematical model for the submerged arc furnace load and renewable energy in the energy system, and obtaining real-time data of the submerged arc furnace load and renewable energy;

[0018] Constructing a prediction model for the submerged arc furnace load and renewable energy based on historical data, and predicting the load change of the submerged arc furnace load and the output power of renewable energy based on the acquired real-time data;

[0019] Coordinate and control the energy system according to the prediction results of the ore-fired furnace load and renewable energy;

[0020] The waste heat tail gas utilization system is controlled to utilize the tail gas.

[0021] A multi-time-scale load power forecasting method comprises the following steps:

[0022] Obtain historical load data and divide the historical data into load data of multiple time scales;

[0023] According to the load data of different time scales, corresponding prediction algorithms are used to build and train the load prediction model of the corresponding time scale;

[0024] The real-time load data is loaded into the load forecasting model of the corresponding time scale to obtain the forecast results of the corresponding time scale.

[0025] A source-grid-load-storage integrated coordinated control method comprises the following steps:

[0026] Power prediction steps: Obtain historical and real-time data of power generation equipment to perform power prediction;

[0027] Load forecasting steps: Obtain historical load data to perform load forecasting

[0028] Day-ahead power generation planning steps: Based on the predicted load changes of the submerged arc furnace and the output power of renewable energy, the renewable energy output plan and the energy storage system charging and discharging plan for the next day are constructed to form a day-ahead power generation plan;

[0029] Intraday rolling optimization step: based on the real-time load demand and power generation capacity of the energy system, the day-ahead power generation plan is revised, and the revised day-ahead power generation plan is dynamically adjusted and optimized;

[0030] Automatic power generation control steps: Control the active power of each generator set in the energy system to achieve real-time balance between power generation output and load demand;

[0031] Automatic voltage control steps: Control reactive voltage equipment in the energy system to achieve online optimized closed-loop control of voltage;

[0032] Source-load coordinated control step: Based on the power generation plan determined by the intraday rolling optimization step, power control instructions are determined and issued to each load, renewable energy source, and energy storage system in the energy system;

[0033] Stable control step: performing stable control on the corresponding equipment according to the power control instruction, and performing system stable control in an emergency.

[0034] A centralized control system and a stabilization control system coordinated control system, comprising: a centralized control module, a stabilization control module and a coordinated control module;

[0035] The centralized control module is used to monitor the operating status and parameters of the energy system and transmit them to the collaborative control module; receive control instructions issued by the collaborative control module, and dispatch and control the energy system;

[0036] The stabilization control module is used to monitor parameter changes of the energy system, perform stability analysis, generate corresponding stabilization control instructions, and transmit them to the collaborative control module;

[0037] The collaborative control module is used to integrate and analyze the information transmitted by the centralized control module and the stabilization control module, generate a comprehensive control strategy, and transmit corresponding control instructions to the centralized control module and the stabilization control module to perform collaborative control of the system.

[0038] A method for optimizing and coordinating control of a wind-solar-storage station, wherein the wind-solar-storage station includes wind power generation equipment, photovoltaic power generation equipment, and a corresponding energy storage system, and the method comprises the following steps:

[0039] Data acquisition step: acquiring operating data information in the wind-solar-storage station;

[0040] Active power optimization and smoothing steps: Based on the operating data information within the wind, solar and storage station, determine whether the power output fluctuations of wind power generation equipment and photovoltaic power generation equipment need to be smoothed. If necessary, the required charge and discharge power is calculated based on the charge and discharge capacity of the energy storage system and the current power fluctuations. The energy storage system is controlled to perform charging and discharging operations based on the charge and discharge power;

[0041] Active power instruction optimization tracking step: comparing the active power instruction transmitted to the wind-solar-storage station with the actual output of the wind-solar-storage station, thereby determining whether the output of the wind-solar-storage station needs to be compensated; if necessary, calculating the compensation value and adjusting the output of the wind-solar-storage station;

[0042] The first frequency regulation step is to obtain the frequency deviation of the wind-solar-storage station grid connection point, determine whether frequency regulation control is required, and if necessary, adjust the output power of each device in the wind-solar-storage station.

[0043] A multi-source adaptive power generation coordinated control method comprises the following steps:

[0044] Obtain status data of each power generation equipment in the power grid;

[0045] Federated learning is used to centrally train the status data of each power generation device to obtain a global power generation prediction model. The obtained global power generation prediction model is combined with the physical model of the corresponding power generation device to obtain an overall prediction model.

[0046] According to the real-time status data and optimization objectives of each power generation device, the power generation control strategy and parameters of the overall prediction model are dynamically adjusted, and the control strategy of each power generation device is obtained using the adjusted overall prediction model.

[0047] A composite allocation method for optimizing efficiency includes the following steps:

[0048] Based on real-time data from the power system, a composite allocation algorithm is used to select the optimal energy allocation plan for each power generation equipment and load. The composite allocation algorithm is composed of a combination of multiple optimization strategies;

[0049] According to the optimal energy distribution plan, corresponding control instructions are generated to control and adjust each power generation equipment and load.

[0050] A multi-energy emergency machine-grid coordination system, comprising:

[0051] Wide-area dynamic synchronous monitoring system for synchronous dynamic monitoring of transient disturbances and faults in energy systems;

[0052] Rapid collaborative control system, used for rapid response and collaborative control of different types of power generation equipment in the energy system;

[0053] Grid stability control system, used to stabilize and regulate the grid of the energy system;

[0054] The energy storage frequency stabilization cooperative control system is used to achieve frequency stabilization and coordinated control of the energy storage system.

[0055] An automated intelligent power supply network reconstruction method comprises the following steps:

[0056] Obtain status data of the power supply network in the energy system and perform network topology analysis and fault diagnosis based on the status data; if a power supply network failure occurs, obtain a power supply network reconstruction plan based on the preset power supply optimization strategy;

[0057] The power supply network is topologically reconfigured according to the power supply network reconstruction plan.

[0058] A five-line-of-defense isolated grid stability control method includes the following steps:

[0059] Monitor the energy system for faults. If a fault occurs, identify the faulty area in the energy system within the first moment of occurrence and isolate the faulty area through pre-set protection components.

[0060] Reconstruct the power supply network of the energy system within a second after the fault area is isolated;

[0061] After a third period of time after the fault area is isolated, the power balance and frequency recovery of the energy system are performed by controlling the output of the power generation equipment in the energy system and adjusting the load;

[0062] If the frequency of the energy system is within the first unstable range, the frequency of the energy system is controlled by means of low-frequency and low-voltage load shedding and high-frequency generator shedding control.

[0063] If the frequency of the energy system is within the second unstable interval, the energy system is divided into minimum power generation systems, and each minimum power generation system is started.

[0064] An independent microgrid hierarchical control system, comprising:

[0065] The energy management layer is used to monitor and manage the energy supply and demand of the energy system, generate energy scheduling instructions, and adjust the energy scheduling instructions in real time according to the execution results of the execution layer;

[0066] The control layer is used to formulate corresponding scheduling strategies according to energy scheduling instructions and generate control instructions;

[0067] The execution layer is used to regulate the energy of the equipment in the energy system according to the control instructions transmitted by the control layer.

[0068] An intelligent unmanned operation system, comprising:

[0069] An unmanned operation host, an intelligent analysis host and a variety of automatic data collection equipment, wherein the unmanned operation host is connected to the intelligent analysis host and the various automatic data collection equipment respectively;

[0070] The unmanned operation host is used to issue control instructions to each automatic data acquisition device and receive data transmitted by each automatic data acquisition device;

[0071] The intelligent analysis host is used to analyze the data collected by the unmanned operation host to form data analysis results.

[0072] The present invention has the following beneficial effects:

[0073] (1) Optimizing energy utilization: As an important part of the energy system, the high energy consumption of the submerged arc furnace means high energy consumption and waste. The introduction of a high proportion of new energy can provide a green and environmentally friendly energy alternative. Through the application of control methods, the coordinated supply of submerged arc furnace load and new energy can be achieved, optimizing energy utilization efficiency and reducing energy waste.

[0074] (2) Environmental protection and low-carbon development: The metallurgical industry is one of the industries with high energy consumption and pollutant emissions. The application of submerged arc furnace production and energy system control methods based on new energy power supply can achieve coordination and optimization between the energy demand of submerged arc furnace load and new energy power supply. By reducing dependence on traditional fossil energy and reducing greenhouse gas emissions, the goals of environmental protection and low-carbon development can be achieved.

[0075] (3) Improve the stability and reliability of the energy system: The characteristics of the submerged arc furnace load and the high proportion of renewable energy bring about energy volatility and uncertainty, which poses a challenge to the stable operation of the energy system. Through the application of control methods, the status of the submerged arc furnace load and renewable energy power supply can be monitored in real time, and corresponding adjustments and controls can be made according to preset conditions to improve the stability and reliability of the energy system and reduce the risk of system failures and power outages.

[0076] (4) Improving the competitiveness of the metallurgical industry: The development of the metallurgical industry requires reducing energy costs, improving production efficiency and environmental sustainability. The application of submerged arc furnace production and energy system control methods based on new energy power supply can optimize the energy supply structure, reduce operating costs, improve energy utilization efficiency, and enhance the competitiveness of metallurgical enterprises.

[0077] In summary, the significance and logic of a control method for submerged arc furnace production and energy systems powered by renewable energy lies in achieving efficient energy utilization, environmental protection, stable operation of the energy system, and enhanced competitiveness in the metallurgical industry by coordinating and optimizing the relationship between submerged arc furnace load and renewable energy power supply. The application of this control method will help advance the metallurgical industry towards green, environmentally friendly, and sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] FIG1 is a schematic diagram of the architecture of a submerged arc furnace production and energy system based on renewable energy power supply provided in Example 1 of the present invention;

[0079] FIG2 is a schematic diagram of the architecture of an energy control system for a submerged arc furnace production and energy system based on renewable energy power supply provided in Example 1 of the present invention;

[0080] FIG3 is a schematic diagram of the specific structure of a submerged arc furnace production and energy system based on renewable energy power supply provided in Example 1 of the present invention;

[0081] FIG4 is a schematic diagram of a coordinated control system of a centralized control system and a stabilization control system provided in Example 4 of the present invention;

[0082] FIG5 is a schematic diagram of a multi-energy emergency machine-grid coordination system provided in Example 8 of the present invention;

[0083] FIG6 is a schematic diagram of three lines of defense in an existing power system provided in Example 10 of the present invention;

[0084] FIG7 is a schematic diagram of an isolated network stability control method based on five defense lines provided in Example 10 of the present invention;

[0085] FIG8 is a schematic structural diagram of an intelligent unmanned operation system provided in Example 11 of the present invention. DETAILED DESCRIPTION

[0086] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments. This embodiment is implemented based on the technical solution of the present invention, and provides a detailed implementation method and specific operating process. Obviously, the described embodiment is only an embodiment of a part of the present invention, not all embodiments, and the protection scope of the present invention is not limited to the following embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present invention.

[0087] Example 1

[0088] As shown in Figure 1, this embodiment provides a submerged arc furnace production and energy system based on renewable energy power supply, including: a power transmission and distribution system, a renewable energy power generation system, an energy storage system and a submerged arc furnace production system, and the power transmission and distribution system is respectively connected to the renewable energy power generation system, the energy storage system and the submerged arc furnace production system.

[0089] The specific functions of each system are:

[0090] Submerged arc furnace production systems to generate heat and electricity;

[0091] Renewable energy generation systems for providing electricity supply from renewable energy sources;

[0092] Energy storage systems, used to receive and store excess electricity generated by renewable energy power generation systems and to balance energy fluctuations in submerged arc furnace production systems;

[0093] The power transmission and distribution system is connected to the ore-fired furnace production system, renewable energy power generation system and energy storage system, and is used to coordinate the scheduling and stability control of the entire energy system.

[0094] Optionally, as shown in FIG3 , the specific structures of the above components are:

[0095] a) Renewable energy power generation system:

[0096] Including wind turbines, photovoltaic arrays, hydropower equipment, etc., which convert natural resources into electrical energy through the conversion of renewable energy; these devices input the generated electrical energy into the energy system to provide the system with clean, renewable electricity.

[0097] b) Submerged arc furnace production system:

[0098] Submerged arc furnaces, a key component on the load side, burn metallurgical raw materials to generate heat for the smelting process. The operating characteristics of submerged arc furnaces are closely related to the stability of the energy system. By modeling and predicting the characteristics of submerged arc furnace loads, it is possible to adjust the furnace load to meet energy demand and optimize energy efficiency.

[0099] c) Energy storage system:

[0100] Energy storage systems, including battery energy storage systems and supercapacitors, are used to receive and store excess electricity generated by renewable energy generation equipment and balance energy fluctuations in the submerged arc furnace load. The energy storage system releases stored energy during peak energy demand periods, ensuring a stable energy supply.

[0101] d) Power transmission and distribution system:

[0102] It is used to monitor and control the overall operation of the energy system, realize the coordinated scheduling of integrated source, grid, load and storage, and the stability control of the microgrid, ensuring that key parameters such as voltage and frequency are within a reasonable range.

[0103] The connections and logical relationships between the above components / parts are as follows:

[0104] a) The submerged arc furnace production system is the main load of the energy system, generating heat and electricity demand.

[0105] b) The renewable energy power generation system provides electricity through wind turbines, photovoltaic panels, hydropower equipment, etc., and its output power is related to the load demand of the submerged arc furnace.

[0106] c) Energy storage systems are used to store and release electricity to balance the volatility of renewable energy and the load demand of the submerged arc furnace. The energy storage system is interconnected with renewable energy generation equipment and the submerged arc furnace. The balance between energy supply and demand is regulated by controlling the charging and discharging processes of the energy storage system.

[0107] e) The transmission and distribution system is the brain of the entire energy system, responsible for monitoring the operating status and data of each component / section and formulating coordinated scheduling strategies for the integrated power generation, grid, load, and storage. Furthermore, the transmission and distribution system is responsible for energy system stability control, ensuring that key parameters such as voltage and frequency remain within reasonable ranges. The transmission and distribution system connects and interacts with the renewable energy generation system, energy storage system, and submerged arc furnace production system through data communication and control signals.

[0108] Preferably, the above-mentioned submerged arc furnace production and energy system further includes an energy control system, which includes:

[0109] Renewable energy power generation control system, used to control the operation of renewable energy power generation system;

[0110] Energy storage control system, used to control the operation of the energy storage system;

[0111] Submerged arc furnace production control system, used to control the operation of the submerged arc furnace production system;

[0112] The integrated control system is used to carry out integrated control of the ore-fired furnace production and energy system through the power transmission and distribution system, send control instructions to the renewable energy power generation control system and the ore-fired furnace production control system, and receive control feedback; receive dispatch instructions from the energy storage control system and provide feedback to the energy storage control system.

[0113] As a preferred embodiment, the submerged arc furnace production and energy system further includes an exhaust gas recycling system, which is connected to the submerged arc furnace production system and the power transmission and distribution system respectively;

[0114] The energy control system also includes an exhaust gas recycling control system, which is used to control the operation of the exhaust gas recycling system.

[0115] Specifically, the tail gas recycling control system is used to collect and process the tail gas and waste heat of the blast furnace production system, and realize the comprehensive utilization of the tail gas by converting it into renewable energy or other available resources, thereby reducing environmental pollution and energy waste.

[0116] Specifically, these include gas storage tanks and gas-fired generator sets. Gas storage tanks are devices used to store compressed gas. In submerged arc furnace production and energy systems powered by renewable energy, gas storage tanks are used to store exhaust gas generated by the submerged arc furnaces so that it can be supplied to gas-fired generator sets when needed. Gas-fired generator sets are power generation equipment that utilizes waste heat and exhaust gas. Their output voltage and frequency are the primary support for the system. Furthermore, they can adjust their operating mode based on system needs and the availability of renewable energy, providing stable power output.

[0117] As a preferred embodiment, the submerged arc furnace production and energy system further includes an external power grid connected to the power transmission and distribution system;

[0118] The energy control system also includes a power grid dispatching system, which is used to dispatch energy to the external power grid to maintain the energy balance of the submerged arc furnace production and the energy system.

[0119] This embodiment also provides a method for controlling the production and energy system of the submerged arc furnace based on new energy power supply, including the following steps:

[0120] Establish a mathematical model for the submerged arc furnace load and renewable energy in the energy system, and obtain real-time data on the submerged arc furnace load and renewable energy;

[0121] Build a prediction model for submerged arc furnace load and renewable energy based on historical data, and predict the load changes of submerged arc furnace load and the output power of renewable energy based on the real-time data obtained;

[0122] Coordinate and control the energy system based on the forecast results of the submerged arc furnace load and renewable energy;

[0123] Control the exhaust gas utilization of the waste heat exhaust gas utilization system.

[0124] Optionally, the control method further includes:

[0125] Based on multi-machine coordinated control and stability analysis, the secondary system stability control strategy is implemented to ensure the stable operation of the energy system;

[0126] Evaluate the control effectiveness of the energy system.

[0127] Optionally, the control method specifically includes the following steps:

[0128] Step 1: System modeling and data acquisition

[0129] a) Establish mathematical models of the submerged arc furnace load and renewable energy, including the heat load model of the submerged arc furnace and the electric power model of renewable energy.

[0130] b) Obtain real-time data on submerged arc furnace load and renewable energy through real-time monitoring systems, sensors and data acquisition systems.

[0131] Step 2: Load Forecasting and Renewable Energy Forecasting

[0132] a) Use historical load data and machine learning algorithms to establish a prediction model for the load of the submerged arc furnace and predict the load change trend in the future.

[0133] b) Predict the generation of renewable energy based on weather data and machine learning algorithms, including the predicted power of renewable energy such as wind power generation and photovoltaic power generation.

[0134] Step 3: Energy system dispatch and coordinated control

[0135] a) Based on the load forecast and renewable energy forecast results, formulate a coordinated control strategy for the integration of source, grid, load and storage.

[0136] b) Adjust the load of the submerged arc furnace to meet energy demand and optimize energy utilization efficiency.

[0137] c) Dispatching the injection or consumption of renewable energy to balance supply and demand and increase the proportion of renewable energy utilization in the system.

[0138] d) Control the charging and discharging process of the energy storage system to balance load fluctuations and renewable energy fluctuations.

[0139] e) Consider multi-machine coordinated control and microgrid stability to achieve stable operation of the energy system.

[0140] Step 4: Exhaust gas utilization and secondary system stability control

[0141] a) Use tail gas utilization technology to convert the exhaust gas and waste heat of the submerged arc furnace into useful energy to improve energy utilization efficiency.

[0142] b) Based on multi-machine coordinated control and stability analysis, implement secondary system stability control strategy to ensure stable operation of the energy system.

[0143] Step 5: System effectiveness evaluation

[0144] a) Real-time monitoring of energy consumption data, including electricity, heating, gas, and heat, through sensors and data acquisition equipment.

[0145] The specific process of the above steps can be:

[0146] Load Forecasting

[0147] Take the Long Short-Term Memory (LSTM) algorithm as an example. The specific workflow is as follows:

[0148] 1. Data collection: Collect historical data on the submerged arc furnace load, including hourly load values ​​and related environmental factors (such as temperature, humidity, etc.).

[0149] 2. Data preprocessing: Preprocess the collected data, including missing value processing, outlier processing and data normalization.

[0150] 3. Feature Engineering: Based on the characteristics of the problem, select appropriate features for extraction, such as time features, frequency domain features, or other field-related features.

[0151] 4. Data partitioning: Divide the dataset into training and test sets for model training and evaluation.

[0152] 5. LSTM model establishment: Build the LSTM model, including setting the number of network layers, number of hidden units, and other hyperparameters.

[0153] 6. Model training: Use the training set to train the LSTM model, and continuously adjust the model parameters through the backpropagation algorithm to minimize the prediction error.

[0154] 7. Model evaluation: Use the test set to evaluate the performance of the model. Metrics such as Root Mean Squared Error (RMSE) or Mean Absolute Percentage Error (MAPE) can be used.

[0155] 8. Model optimization: Based on the evaluation results, optimize the model, such as adjusting the network structure, adjusting hyperparameters, or using ensemble learning methods.

[0156] 9. Model application: Use the optimized LSTM model to predict future loads and obtain prediction results for the submerged arc furnace load.

[0157] Renewable energy forecasts

[0158] Taking wind power generation as an example, a machine learning method is used to build a wind power generation model. The Support Vector Regression (SVR) algorithm is used as an example. The specific workflow is as follows:

[0159] 1. Data collection: Collect historical wind speed and wind power data.

[0160] 2. Data preprocessing: Preprocess the collected data, including missing value processing, outlier processing and data normalization.

[0161] 3. Feature Engineering: Based on the characteristics of wind power generation, select appropriate features for extraction, such as statistical characteristics of wind speed and time series characteristics.

[0162] 4. Data partitioning: Divide the dataset into training and test sets for model training and evaluation.

[0163] 5. SVR model establishment: Establish an SVR model based on the training set data and select appropriate kernel functions and regularization parameters.

[0164] 6. Model training: Use the training set to train the SVR model and adjust the model parameters to fit the nonlinear relationship between wind speed and wind power generation.

[0165] 7. Model evaluation: Use the test set to evaluate the performance of the model. Metrics such as Root Mean Squared Error (RMSE) or Mean Absolute Percentage Error (MAPE) can be used.

[0166] 8. Model optimization: Based on the evaluation results, optimize the model, such as adjusting the kernel function type, adjusting the regularization parameters, or performing feature selection.

[0167] 9. Model application: Use the optimized SVR model to predict wind speed data for future periods and then predict the power output of wind power generation.

[0168] Energy system dispatch and coordinated control: integrated coordinated control method for source, grid, load and storage

[0169] 1. Data acquisition: Obtain real-time data on the source-grid-load-storage system, including load demand, renewable energy production, and energy storage system status.

[0170] 2. Coordinated control strategy: Develop a coordinated control strategy that integrates power generation, grid, load, and storage, and achieves stable system operation and optimized energy utilization by comprehensively considering load demand, renewable energy supply, and the status of the energy storage system.

[0171] 3. Control Algorithms: Advanced control algorithms, such as model predictive control (MPC), reinforcement learning (RL), or fuzzy control, are used to coordinate the control of the source, grid, load, and storage system. These algorithms make decisions based on real-time data and generate corresponding control signals to adjust load, renewable energy injection, and the charging and discharging of the energy storage system.

[0172] 4. Control implementation: Apply control signals to execution units in the system, such as load controllers, renewable energy controllers, and energy storage system controllers, to implement a coordinated control strategy for integrated source, grid, load, and storage.

[0173] Energy system dispatch and coordinated control: microgrid stability control

[0174] Data acquisition: Acquire real-time data of each generator set in the microgrid system, such as generator output power, voltage, frequency, etc.

[0175] 1. Multi-machine coordinated control strategy: Develop a microgrid stability control strategy based on multi-machine coordination, and achieve stable operation of the microgrid through coordinated control between generator sets.

[0176] 2. Control Algorithm: A multi-machine coordinated control algorithm, such as distributed coordinated control, centralized coordinated control, or communication network-based coordinated control, is used to coordinate the control of the generators in the microgrid system. The algorithm makes decisions based on real-time data and generates corresponding control signals to adjust the operating status of the generators.

[0177] 3. Control Implementation: Apply control signals to the generator control system to implement a multi-machine coordinated microgrid stability control strategy. Stable microgrid operation is achieved by adjusting parameters such as generator output power, voltage, and frequency.

[0178] In step 2, as a preferred implementation, a multi-time-scale load power forecasting method is adopted for load forecasting, taking into account the load forecasting requirements of multiple time scales to improve the accuracy of load forecasting.

[0179] In step 3, an integrated coordinated control system for power generation, grid load, and storage can be used for operational control. Specifically, this involves the integrated application of functional modules such as power forecasting, load forecasting, day-ahead generation planning, intraday rolling optimization, automatic generation control, grid connection control, automatic voltage control, power-load coordination control, and stability control. This system aims to maximize local consumption of renewable energy and mitigate fluctuations in renewable energy power by optimizing energy storage charging and discharging strategies, while ensuring maximum production load and grid stability. It also incorporates frequency and peak shaving capabilities, optimizing grid-connected technical performance indicators.

[0180] Preferably, the above-mentioned integrated coordinated control system based on source, grid, load and storage can be divided into a centralized control system and a stabilization control system. The centralized control system is mainly responsible for real-time monitoring, data collection and operation scheduling of the power system, while the stabilization control system focuses on the stability and safety of the power system. A collaborative control method for the centralized control system and the stabilization control system is proposed to achieve effective interaction and collaboration between them, so as to optimize the operation control strategy of the power system and improve the stability, reliability and operation efficiency of the system.

[0181] Preferably, during the control process of the integrated power generation, grid-load-storage coordinated control system, a wind, solar, and storage station optimization coordinated control system and method is provided for controlling the wind, solar, and storage stations in the system, enabling energy storage and dispatch control for wind and photovoltaic power generation. This system is primarily used for monitoring and controlling station-side equipment, collecting and uploading data, and communicating with the integrated power generation, grid-load-storage coordinated control center.

[0182] Preferably, the automatic power generation control of the source-grid-load-storage integrated coordinated control system adopts a multi-source adaptive power generation coordinated control system, which focuses on optimizing and innovating the automatic generation control (AGC) functional module and realizing automatic coordinated control of multiple types of power sources.

[0183] Preferably, the source-load coordinated control of the source-grid-load-storage integrated coordinated control system adopts a composite distribution strategy with efficiency optimization as the goal, aiming to achieve efficient energy distribution between multiple power sources and loads in the power system, optimize system operation efficiency, and improve energy utilization efficiency.

[0184] Preferably, in emergency situations in the power system, such as sudden disturbances or failures in power generation sources or loads such as gas turbines, wind power, and photovoltaics, this embodiment proposes a multi-energy emergency machine-grid coordination system and method. Through the configuration of the multi-energy emergency machine-grid coordination system, the functions of wide-area dynamic synchronous monitoring, rapid collaborative control, and stabilization system are realized to ensure the safe and stable operation of the power system in emergency situations, avoid the adverse effects on the power grid when power generation sources or loads fail, and achieve rapid and balanced power generation and consumption.

[0185] Further preferably, during the process of wide-area dynamic synchronous monitoring and rapid collaborative control, this embodiment also proposes an automated intelligent power supply network reconstruction system, which realizes rapid reconstruction and fault handling of the power supply network through automated and intelligent methods.

[0186] Further preferably, in the process of stabilizing the control system, this embodiment also proposes an isolated grid stabilization control system and method based on five lines of defense. Through the setting of five lines of defense, a complete and strong defense system is constructed, while achieving the effects of improving rapid response capabilities, realizing high-proportion new energy isolated grid stabilization control, and improving the reliability and stability of the power grid.

[0187] Preferably, in the control process of the above scheme, this embodiment proposes a hierarchical control mode for independent microgrids. This mode aims to achieve coordinated control of each level in the independent microgrid system through a hierarchical control strategy to optimize energy management and improve the reliability and economy of the power system.

[0188] In step 4, preferably, in order to achieve efficient energy system data collection, this embodiment proposes an intelligent unmanned operation system and method thereof to realize unmanned operation of 220kV booster station and 220kV booster station step-down station, including equipment joint unmanned operation, data collection and analysis, real-time monitoring and intelligent linkage and other functions.

[0189] b) Based on real-time monitoring data and carbon emission calculation models, carbon emission reports are automatically generated, providing detailed energy consumption and carbon emission data, and performing analysis and interpretation.

[0190] c) Employ intelligent algorithms and data analysis techniques to simulate different emission reduction strategies and plans and evaluate their effectiveness. Based on the simulation results, we optimize emission reduction paths and develop scientific and effective carbon reduction plans to reduce the unit carbon emissions of our products.

[0191] d) Based on the results of the performance evaluation, if the carbon emissions reduction of the energy system meets certain standards, a green energy certificate may be issued to prove its environmentally friendly operation.

[0192] Example 2

[0193] This embodiment provides a multi-timescale load power forecasting method to address the following deficiencies in existing load forecasting solutions:

[0194] 1.1) Limitations of traditional statistical methods: Traditional statistical methods often ignore the dynamic changes and nonlinear relationships of load characteristics in load forecasting, and cannot accurately capture the complexity and volatility of loads in the steel industry.

[0195] 1.2) Single-timescale forecasting: Existing solutions often focus on load forecasting at a single timescale, failing to meet the steel industry’s demand for load forecasting across diverse timeframes. This results in errors and uncertainties in long-, medium-, and short-term forecasts.

[0196] 1.3) Ignoring Comprehensive Analysis of Influencing Factors: Existing solutions often overlook the complex relationship between load and its influencing factors, such as meteorological factors and special events. These factors have a significant impact on the load of the steel industry, and ignoring them may lead to deviations in forecast results.

[0197] 1.4) Lack of adaptability and flexibility: Existing solutions lack adaptability and flexibility and cannot be adjusted and optimized according to different data and load characteristics. This limits the accuracy and stability of the prediction model.

[0198] 1.5) Lack of real-time performance: Existing solutions often rely on offline calculations and historical data and cannot reflect current load changes in a timely manner. This has certain limitations in practical applications.

[0199] The above multi-time-scale load power forecasting method aims to achieve the following goals:

[0200] 1.1) Improve load forecasting accuracy: By establishing a load characteristic model, fully considering the dynamic changes and nonlinear relationships of the load, we can accurately predict the load power. Introducing new algorithms and models will improve the accuracy and reliability of load forecasting.

[0201] 1.2) Considering multi-timescale load forecasting needs: Provide multi-timescale load forecasting, including ultra-short-term, short-term, and long-term forecasts. By appropriately selecting forecasting algorithms and models, the steel industry's needs for load forecasting in different timeframes can be met.

[0202] 1.3) Comprehensive analysis of load influencing factors: The relationship between load and its influencing factors, such as meteorological factors and special events, will be comprehensively considered. By comprehensively analyzing the impact of these factors on load, the accuracy and reliability of load forecasting can be improved.

[0203] 1.4) Provide an adaptive and flexible forecasting model: This provides an adaptive and flexible load forecasting model that can be adjusted and optimized based on different data and load characteristics. This can improve the accuracy and stability of the forecast results.

[0204] 1.5) Real-time load forecasting: Real-time load forecasting can promptly reflect current load changes. By introducing real-time data and calculation methods, the real-time nature and responsiveness of load forecasting can be improved.

[0205] The multi-time-scale load power forecasting method includes the following steps:

[0206] Obtain historical load data and divide the historical data into load data of multiple time scales;

[0207] According to the load data of different time scales, corresponding prediction algorithms are used to build and train the load prediction model of the corresponding time scale;

[0208] The real-time load data is loaded into the load forecasting model of the corresponding time scale to obtain the forecast results of the corresponding time scale.

[0209] To improve the accuracy of load forecasting and take into account the dynamic changes and nonlinear relationships of load characteristics, the above method also extracts features and performs modeling analysis on historical load data to make corresponding forecasts. The specific method can be divided into the following parts:

[0210] 1. Data acquisition and preprocessing module: responsible for collecting historical load data and related influencing factor data of the steel industry, and preprocessing and cleaning the data to provide accurate and reliable input data.

[0211] 2. Feature Extraction and Modeling Module: This module extracts features from the collected data and performs modeling analysis to capture the characteristics and changing patterns of loads in the steel industry. This module uses feature extraction and modeling techniques based on statistical methods and machine learning algorithms.

[0212] 3. Time scale division and forecasting module: According to the time scale requirements of load forecasting, load data is divided into ultra-short-term, short-term and long-term, and corresponding load forecasting models are constructed and optimized for different time scales.

[0213] 4. Forecasting Algorithms and Models: This section includes a variety of load forecasting algorithms and models, such as artificial neural network algorithms, linear extrapolation algorithms, and exponential smoothing algorithms. Based on specific needs and data characteristics, select appropriate algorithms and models for load forecasting.

[0214] 5. Forecast result evaluation and optimization module: This module is used to evaluate the accuracy and reliability of load forecast results, and optimize and adjust the forecast results to improve the accuracy and stability of the forecast.

[0215] The specific processing of the above multi-time-scale load power forecasting method includes:

[0216] 1. Data acquisition and preprocessing module:

[0217] This module is responsible for acquiring historical load data and related influencing factor data from the steel industry. Through data acquisition equipment and sensors, it collects load information and influencing factor data at each moment.

[0218] The preprocessing module preprocesses and cleans the collected data, including removing outliers, filling missing data, standardization and other operations to ensure the accuracy and consistency of the data.

[0219] 2. Feature extraction and modeling module:

[0220] In this module, the basic characteristics and changing patterns of the load are extracted by extracting and analyzing the collected load data and influencing factor data.

[0221] The historical load data is decomposed into basic load components, weather-sensitive load components, and special event load components. The remaining residuals are the random load components at each moment and can be regarded as random time series.

[0222] 3. Time scale division and prediction module:

[0223] This module divides the load data into demand according to the forecast time scale, including ultra-short-term and short-term forecasts.

[0224] The ultra-short-term load forecasting function is used to predict system load at a specific time within the next 0 to 24 hours. For a given period of past load records, after extracting the base load component, weather-sensitive load component, and special event load component, the remaining residual is the random load component at each moment, which can be viewed as a random time series. Forecasts can be performed automatically or manually, and the forecast duration and interval are configurable.

[0225] The short-term load forecasting function is used to predict system load for the next day to week, with time intervals of 1 minute, 5 minutes, 15 minutes, half an hour, and 1 hour. This function provides a variety of forecasting algorithms, such as artificial neural networks, linear extrapolation, and exponential smoothing. Based on the characteristics of the power grid, it conducts correlation analysis between load and its influencing factors and establishes an adaptive combined mathematical model.

[0226] 4. Prediction algorithm and model library:

[0227] This solution provides a variety of load forecasting algorithms and model libraries to meet different data characteristics and forecasting requirements.

[0228] Select appropriate prediction algorithms and models based on specific scenarios and needs, such as artificial neural network algorithms, linear extrapolation algorithms, exponential smoothing algorithms, etc.

[0229] 5. Forecast result evaluation and optimization module:

[0230] This module is used to evaluate the accuracy and reliability of load forecast results. Various evaluation indicators and methods are used to compare the differences between the forecast results and the actual load data, and to perform error analysis.

[0231] Based on the evaluation results, the prediction model is optimized and adjusted to improve the accuracy and stability of the prediction results.

[0232] Connections and logical relationships:

[0233] 1. The data acquisition and preprocessing module provides accurate input data to the feature extraction and modeling module, as well as the time scale division and prediction module.

[0234] The feature extraction and modeling module extracts and models features of the data to obtain a load feature model, which provides input for the time scale division and prediction module.

[0235] 2. The time scale division and prediction module divides the load data into different time scales according to the prediction requirements and uses appropriate prediction algorithms and models for prediction.

[0236] 3. The prediction algorithm and model library provides a variety of prediction algorithms and model options for use in time scale division and prediction modules.

[0237] 4. The prediction result evaluation and optimization module optimizes and adjusts the prediction model by evaluating the accuracy and reliability of the prediction results to improve the accuracy and stability of the prediction results.

[0238] Through the connections and logical relationships between the above components / parts, this solution can achieve the goals of load characteristic modeling and multi-time scale load power forecasting in the steel industry.

[0239] The above multi-time-scale load power forecasting method has the following advantages:

[0240] 1. Accuracy and reliability: By introducing new algorithms and models, and considering multiple influencing factors, this solution can provide accurate and reliable load characteristic modeling and forecasting results, better reflecting the actual changes and trends in the steel industry's load.

[0241] 2. Multi-timescale forecasting: This solution meets the steel industry's demand for load forecasting at different timescales, including ultra-short-term, short-term, and long-term forecasts. It can flexibly divide and forecast timescales, providing more comprehensive and accurate load forecast results.

[0242] 3. Adaptability and Flexibility: This solution utilizes an adaptive combination of mathematical models and multiple forecasting algorithms and model libraries, enabling adjustments and optimization based on different data and load characteristics. It offers a degree of flexibility and can adapt to varying data characteristics and forecasting requirements.

[0243] 4. Real-time and responsiveness: By introducing real-time data and calculation methods, this solution enables real-time load forecasting and promptly reflects current load changes. Its high real-time and responsiveness support rapid decision-making and load adjustments in the steel industry.

[0244] 5. Efficiency and operability: This solution provides a complete load characteristic modeling and forecasting system, including data collection, feature extraction, and forecasting models. It can efficiently perform load forecasting and provide actionable forecast results for the steel industry, supporting business decision-making and operational management.

[0245] With the above advantages, this solution can provide the steel industry with accurate, reliable, flexible and real-time load characteristic modeling and multi-time scale load power forecasting solutions, helping the industry achieve more efficient and sustainable operation management.

[0246] Example 3

[0247] This embodiment provides a source-grid-load-storage integrated coordinated control method and system to address the following deficiencies in existing source-grid-load-storage coordinated control systems:

[0248] 1. The decentralized control system lacks overall coordination, resulting in low scheduling efficiency.

[0249] 2. Traditional power forecasting and load forecasting methods are not accurate enough to meet the needs of complex power systems.

[0250] 3. The lack of day-ahead power generation planning and intraday rolling optimization functions leads to inaccurate power generation plans and the inability to flexibly respond to load changes.

[0251] 4. The automatic generation control and automatic voltage control capabilities are limited, and rapid power regulation and grid stability control cannot be achieved.

[0252] 5. The source-load coordinated control is not flexible enough, and it is unable to fully utilize the potential of renewable energy power generation, and it is unable to accurately control the load.

[0253] 6. The stability control capability needs to be improved, and it lacks the millisecond-level frequency and voltage stability control capability.

[0254] The purpose of this integrated coordinated control system for grid-load and storage is to solve the existing problems of the coordinated control system for grid-load and storage in the Zero Carbon Alloy Industrial Park and provide the following advantages:

[0255] 1. Improve system scheduling efficiency: By integrating multiple functional modules, the overall coordination and optimization of the system can be achieved, the scheduling efficiency can be improved, energy waste can be reduced, and operating costs can be reduced.

[0256] 2. Improve the absorption rate of new energy: Through accurate power forecasting and load forecasting, optimize power generation planning and power control, maximize local absorption of new energy, improve the absorption rate of new energy, and reduce dependence on traditional energy.

[0257] 3. Improve grid stability: Through functions such as automatic power generation control, automatic voltage control and stability control, real-time balance control of power generation and grid voltage is achieved, thereby improving the stability and security of the grid.

[0258] 4. Provide flexible source-load coordinated control: Through comprehensive optimization calculation and command issuance, it realizes power control of wind power, photovoltaic and energy storage systems, and flexibly adjusts the relationship between source, grid and load to meet different load requirements.

[0259] 5. Supports grid-connected and easy control: It has the ability to regulate system peaks and smooth out fluctuations in wind and solar power output. Through the charging and discharging strategies of energy storage, it provides frequency regulation, peak regulation and other services, optimizes grid-connected technical performance indicators, and improves grid-friendly characteristics.

[0260] The method of this scheme mainly includes the following steps:

[0261] Power prediction steps: Obtain historical and real-time data of power generation equipment to perform power prediction;

[0262] Load forecasting steps: Obtain historical load data to perform load forecasting

[0263] Day-ahead power generation planning steps: Based on the predicted load changes of the submerged arc furnace and the output power of renewable energy, the renewable energy output plan and the energy storage system charging and discharging plan for the next day are constructed to form a day-ahead power generation plan;

[0264] Intraday rolling optimization step: based on the real-time load demand and power generation capacity of the energy system, the day-ahead power generation plan is revised, and the revised day-ahead power generation plan is dynamically adjusted and optimized;

[0265] Automatic power generation control steps: Control the active power of each generator set in the energy system to achieve real-time balance between power generation output and load demand;

[0266] Automatic voltage control steps: Control reactive voltage equipment in the energy system to achieve online optimized closed-loop control of voltage;

[0267] Source-load coordinated control step: Based on the power generation plan determined by the intraday rolling optimization step, power control instructions are determined and issued to each load, renewable energy source, and energy storage system in the energy system;

[0268] Stable control step: performing stable control on the corresponding equipment according to the power control instruction, and performing system stable control in an emergency.

[0269] The system of this solution mainly consists of the following components / parts:

[0270] 1. Power Prediction Module

[0271] Data Reception and Storage: This module receives real-time data and forecast data from new energy power stations through SFTP, 104, etc., and parses and uniformly stores the received data.

[0272] Prediction Algorithms: Various prediction algorithms, such as time series analysis and machine learning, are used to predict power based on the received real-time and historical data to generate accurate prediction results.

[0273] Monitoring and Display Interface: This interface provides centralized forecast management through a web-based interface. Users access the system through a unified login interface and can view the corresponding monitoring and analysis interfaces. Forecast results are displayed in both graphical and tabular formats, and data export is supported.

[0274] 2. Load Prediction Module

[0275] Historical Load Query: This module supports the query of historical load data. Users can select the query time range and dimension through the system interface to obtain historical load data and display and analyze it.

[0276] Prediction Parameter Configuration: Users can configure load forecast parameters on the interface, including prediction interval, prediction duration, algorithm selection, etc., to meet different needs.

[0277] Load Prediction Algorithms: Uses artificial neural network algorithms, linear extrapolation algorithms, exponential smoothing algorithms and other algorithms to analyze and model historical load data and predict future system loads.

[0278] 3. Day-Ahead Generation Planning Module

[0279] Wind and solar ultra-short-term power forecasting: Based on the ultra-short-term power forecast results reported by wind and solar power stations, with a time resolution of 15 minutes, power generation forecasts are made by combining wind power, photovoltaic power generation, and the overall output of the power station to generate a day-ahead power generation plan.

[0280] Short-Term Load Forecasting: Based on the short-term load forecasting results, the system load is predicted for the next one day to one week. It supports multiple algorithms, such as artificial neural network algorithms and linear extrapolation algorithms, and establishes an adaptive combined mathematical model to generate load forecast results.

[0281] Generation Planning: Taking into account factors such as ultra-short-term wind and solar power forecasts, short-term load forecasts, and energy storage operating status, a wind power output plan, photovoltaic output plan, and energy storage charging and discharging plan are formulated for 96 daily time periods from the next day to the next several days.

[0282] 4. Intraday Rolling Optimization Module

[0283] Real-Time Revision of Generation Plan: Based on real-time load demand and power generation capacity, the day-ahead power generation plan is revised in real time to ensure its accuracy and adaptability.

[0284] Optimization Algorithms: Optimization algorithms, such as genetic algorithms and simulated annealing algorithms, are used to optimize the revised power generation plan to achieve the goal of system optimization scheduling.

[0285] Rolling Optimization of Generation Plan: Based on the changes in real-time load and power generation capacity, the revised power generation plan is optimized on a rolling basis to achieve dynamic adjustment and optimization of the power generation plan.

[0286] 5. Automatic Generation Control Module

[0287] This module achieves a real-time balance between power generation output and load demand by controlling the active power of generators within its jurisdiction. Its main objectives include maintaining system frequency within acceptable limits relative to rated values, maintaining net exchange power on external interconnection lines within acceptable limits relative to planned values, and achieving automatic coordinated power generation control.

[0288] 6. Automatic Voltage Control Module

[0289] This module implements online, optimized, closed-loop control of grid voltage by controlling reactive voltage devices within wind, solar, and storage stations, such as the reactive output of generators, on-load tap changers (OLTCs), and switchable reactive compensation devices. Its goal is to ensure grid voltage stability and quality, reducing grid losses and improving grid stability through reactive power regulation.

[0290] 7. Source-Load Coordination Control Module

[0291] This module receives active / reactive power commands from the grid dispatcher and performs real-time corrections and optimization calculations based on the current wind / solar output, energy storage operating status, and load status of each wind / solar / storage station, combined with the day-ahead power generation plan. Ultimately, it determines the active / reactive power and load commands for the wind farm, photovoltaic power station, and energy storage system, and sends these commands to the control systems and load control systems at each station, enabling power control of the wind / solar / storage system and the load.

[0292] 8. Stability Control Module

[0293] This module includes a stability control decision-making master station and a stability control rapid power control execution substation. The stability control decision-making master station formulates strategies for adjusting the output of energy storage, wind farms, and photovoltaic stations based on system frequency and voltage deviations, and implements load / unit shedding measures in emergency situations to achieve frequency and voltage stability control within 100 milliseconds. The stability control rapid power control execution substation receives strategy commands from the stability control decision-making master station and, based on the wind, solar, and storage system's operating status, sends active / reactive output commands to the wind, solar, and storage system, achieving millisecond-level frequency and voltage stability control while preventing conflicts with the system's AGC / AVC control commands.

[0294] The logical relationships between the above modules include:

[0295] 1. Power Prediction Module: This module receives real-time and forecast data from new energy power plants and performs data analysis, storage, and centralized management. It uses historical data and forecasting algorithms to predict the power of new energy power plants. The forecast results are used in the operation and decision-making of subsequent modules.

[0296] 2. Load Forecasting Module: This module predicts system load for future time periods based on historical load data and related influencing factors. It uses multiple algorithms, combined with grid characteristics and load data correlation analysis, to establish an adaptive combined mathematical model. The load forecast results are used in the operation and decision-making of subsequent modules.

[0297] 3. Day-Ahead Power Generation Planning Module: This module combines power and load forecasts to develop day-ahead power generation plans for renewable energy power plants. It considers power system balance constraints, network constraints, and renewable energy site constraints, and provides flexible parameter configuration and effectiveness settings. The plan includes wind power output plans, photovoltaic output plans, and energy storage charging and discharging plans.

[0298] 4. Intraday Rolling Plan Module: This module develops a real-time power generation plan from day one to day one, based on power forecasts and energy storage operating status reported by wind, solar, and storage farms, as well as load demand, and performs rolling revisions. It comprehensively considers power balance constraints, grid security constraints, unit operation constraints, and renewable energy generation capacity to achieve centralized optimization of power generation plans.

[0299] 5. Automatic Generation Control Module: This module achieves real-time balance between power generation output and load by controlling the active power of generator sets within the region. It receives instructions from the source-load coordination control module and adjusts the active power of the generator sets based on load changes. The automatic generation control module primarily implements frequency and peak regulation functions, ensuring that system frequency and voltage remain within acceptable ranges, and provides automatic generation coordination and control capabilities.

[0300] 6. Automatic Voltage Control Module: This module implements online closed-loop optimization of grid voltage by controlling the reactive power voltage devices in power plants. Based on real-time grid operating data, it controls the reactive power output of generators, reactive power compensation devices, and voltage-regulating transformers. The automatic voltage control module ensures acceptable grid voltage quality and reduces network losses.

[0301] 7. Source-Load Coordination Control Module: This module receives active / reactive power commands from the grid dispatcher and, based on the wind, solar, and storage station's output, energy storage operating status, and load, determines the active / reactive power and load commands for the generator sets through comprehensive optimization calculations. It then issues these commands to the control systems and load control systems at each station, achieving coordinated control of power generation and load.

[0302] 8. Stability Control Module: This module formulates output regulation strategies for energy storage, wind farms, and photovoltaic stations based on system frequency and voltage deviations. In emergency situations, it can implement measures such as load shedding / generator removal to achieve frequency and voltage stability within 100 milliseconds. The goal of the stability control module is to ensure safe and stable operation of the power grid.

[0303] The logical relationships between these modules are collaborative and interdependent. The power forecasting module and the load forecasting module provide forecast data for use by the day-ahead generation planning module and the intraday rolling planning module. These planning modules generate power generation plans and, through the source-load coordination control module, issue instructions to the automatic generation control module and the automatic voltage control module. The stability control module monitors system frequency and voltage and adjusts generator output accordingly. The coordinated work of these modules enables integrated control of power generation, grid, load, and storage, maximizing the utilization of renewable energy, ensuring grid stability, and optimizing operation.

[0304] The advantages of this solution include:

[0305] 1. Integrated design: By integrating multiple functional modules, the overall coordination and optimization of the system can be achieved, and the scheduling efficiency and control accuracy can be improved.

[0306] 2. Improved new energy consumption rate: Through accurate power and load forecasting, power generation planning and power control are optimized to maximize local consumption of new energy and reduce dependence on traditional energy.

[0307] 3. Improved grid stability: Through functions such as automatic power generation control, automatic voltage control and stability control, real-time balance control of power generation and grid voltage is achieved, improving the stability and security of the grid.

[0308] 4. Flexible source-load coordination control: Through comprehensive optimization calculation and command issuance, power control of wind power, photovoltaic and energy storage systems is achieved, and the relationship between source, grid and load is flexibly adjusted to meet different load requirements.

[0309] 5. Good grid-connected control capability: It has the ability to regulate system peaks and smooth out fluctuations in wind and solar power output, provide frequency regulation, peak regulation and other services, optimize grid-connected technical performance indicators, and improve grid-friendly characteristics.

[0310] Advantages of structural improvement:

[0311] 1. Centralized monitoring and management: The system displays forecast data, real-time data, and operating status of each station in the form of charts and tables, enabling centralized monitoring and alarming of system operations. It also provides intuitive data display and export functions to facilitate user understanding, analysis, and decision-making.

[0312] 2. Visual interface: Through the design of the human-computer interface, it provides functions such as historical load data query, forecast parameter configuration, and forecast load data query. It displays data content in an intuitive form, supports data export and comparative analysis, and is convenient for user operation and use.

[0313] Example 4

[0314] This embodiment provides a coordinated control system of a centralized control system and a stabilization control system to solve the following problems:

[0315] The centralized control system and stability control system commonly used in power systems have limitations due to their independent operation. The centralized control system is primarily responsible for real-time monitoring, data collection, and operational scheduling of the power system, while the stability control system focuses on the stability and security of the power system. However, in practice, these two systems often operate independently and lack effective coordination mechanisms, resulting in suboptimal overall performance improvements for the power system.

[0316] The purpose of this collaborative control method between the centralized control system and the stability control system is to solve the problem of independent operation of the existing centralized control system and the stability control system, and to propose a collaborative control method between the centralized control system and the stability control system to achieve effective interaction and collaboration between them, so as to optimize the operation control strategy of the power system and improve the stability, reliability and operation efficiency of the system.

[0317] This solution mainly consists of the following major components / parts, each of which plays an important role in achieving the joint operation of the centralized control system and the stability control system:

[0318] Centralized Control System (Safety Zones I and II): The centralized control system is responsible for real-time monitoring, data collection, and operational scheduling of the power system. It includes functions such as monitoring and operating subsystems, intelligent operation tickets and error prevention, relay protection, and a fault recording master station. The centralized control system exchanges data and shares information through a collaborative mechanism with the stability control system, achieving overall control and optimization of the power system.

[0319] Stability and Control System (Safety Zone III): The stability and control system focuses on the stability and safety of the power system. It includes functions such as a power generation and consumption forecasting system, a production monitoring and statistical analysis subsystem, and other functions. The stability and control system works in conjunction with the centralized control system, exchanging control commands and operating status information to achieve stable control and optimization of the power system.

[0320] Collaborative Control Module: The collaborative control module is the core component for the joint operation of the centralized control system and the stability control system. It coordinates data exchange and information sharing between the centralized control system and the stability control system. Through real-time data transmission and processing, the collaborative control module achieves close linkage between the centralized control system and the stability control system, ensuring the consistency and effectiveness of the system's overall operational control strategy.

[0321] As shown in Figure 4, the specific scheme of the collaborative control method of the centralized control system and the stabilization control system includes:

[0322] Centralized Control System (Safety Zones I and II): The centralized control system monitors the power system's operating status and parameters in real time, collects relevant data, and transmits it to the collaborative control module. Simultaneously, the centralized control system receives control commands from the collaborative control module to dispatch and control the power system's operations. Specific functions include SCADA, fault alarms, and remote control.

[0323] Stability and Control System (Safety Zone III): The stability and control system monitors parameters such as frequency and voltage in the power system and generates corresponding control instructions based on stability analysis and control strategies. These control instructions are transmitted to the centralized control system through the collaborative control module to adjust the power system's operating status and ensure system stability and safety. Specific functions include power generation and consumption forecasting, as well as load forecasting.

[0324] Collaborative Control Module: This module integrates and coordinates the functions of the centralized control system and the stability control system. It monitors the operating status and parameters of the centralized control system and the stability control system in real time and integrates and analyzes the data. The collaborative control module generates comprehensive control strategies and transmits corresponding control instructions to the centralized control system and the stability control system, achieving coordinated control and optimized operation.

[0325] Through the combined efforts of the centralized control system and the stability control system, the integrated power monitoring and stability control system achieves overall control and optimization of the power system. The centralized control system is responsible for real-time monitoring and dispatching, the stability control system focuses on stability and safety, and the collaborative control module provides integration and coordination, ensuring stable operation and optimized control of the system.

[0326] Achieve the following effects:

[0327] Comprehensive performance optimization: Through the joint work of the centralized control system and the stability control system, the comprehensive regulation and optimization of the power system can be achieved, and the stability, reliability and operation efficiency of the system can be improved.

[0328] Data sharing and collaboration: Data exchange and information sharing between the centralized control system and the stability control system enable the two systems to share operating status and control strategies in real time, achieving more efficient system control.

[0329] Stability analysis and control: The integrated power monitoring and stability control system has the stability analysis and control functions of the stability control system, which can effectively monitor and control the operating status of the power system to ensure the stable operation of the system.

[0330] Security protection configuration: The system platform construction complies with the requirements of the security protection regulations for power monitoring systems. It adopts the basic principles of security zoning, network dedicating, horizontal isolation and vertical authentication, and configures security protection equipment to ensure the information security and reliability of the system.

[0331] Through the coordinated control of the centralized control system and the stability control system, this solution can achieve overall optimization of the power system and improve the system's stability, reliability and operating efficiency.

[0332] Example 5

[0333] This embodiment provides a wind, solar, and storage station optimization and coordination control system and method. Current similar solutions have some drawbacks, such as:

[0334] Incomplete or inaccurate data collection: Existing solutions have some limitations in data collection, resulting in the inability to obtain comprehensive and accurate operating information of station-side equipment.

[0335] Inflexible control strategy: The control strategy of the existing solution is relatively fixed, lacking flexibility and autonomy, and cannot adapt to the optimization scheduling needs under different scenarios and operating conditions.

[0336] Existing literature and patents have solved some of the problems, but there are the following differences compared with this solution:

[0337] Data acquisition gateway: The data acquisition method in existing solutions may have problems with incomplete information or unstable transmission. The data acquisition gateway in this solution can ensure that the operating status of station-side equipment, substation information, power forecast information, power consumption information, fault recording information, etc. are fully and accurately uploaded to the integrated source, grid, load and storage coordination control center.

[0338] Station Optimization Coordination Control Device: The coordination control devices in existing solutions lack autonomous functional modules and flexible control strategies, resulting in limited optimization in command control and automatic control. However, the station optimization coordination control device in this solution supports both wind, solar, and energy storage command control and automatic control modes. It also features functional modules such as active power optimization and smoothing, active power command optimization tracking, and primary frequency regulation, enabling more flexible and intelligent dispatching control.

[0339] This solution aims to address the limitations of existing solutions in data collection and scheduling control. Its main objectives include:

[0340] Realize comprehensive and accurate data collection of station-side equipment operating status, booster station information, power forecast information, power information, fault recording information, etc.

[0341] Provide flexible control strategies to adapt to the optimization scheduling needs under different scenarios and operating conditions.

[0342] The optimized coordinated control method of wind, solar and storage stations in this scheme includes:

[0343] Data acquisition step: acquiring operating data information in the wind-solar-storage station;

[0344] Active power optimization and smoothing steps: Based on the operating data information within the wind, solar and storage station, determine whether the power output fluctuations of wind power generation equipment and photovoltaic power generation equipment need to be smoothed. If necessary, the required charge and discharge power is calculated based on the charge and discharge capacity of the energy storage system and the current power fluctuations. The energy storage system is controlled to perform charging and discharging operations based on the charge and discharge power;

[0345] Active power instruction optimization tracking step: comparing the active power instruction transmitted to the wind-solar-storage station with the actual output of the wind-solar-storage station, thereby determining whether the output of the wind-solar-storage station needs to be compensated; if necessary, calculating the compensation value and adjusting the output of the wind-solar-storage station;

[0346] The first frequency regulation step is to obtain the frequency deviation of the wind-solar-storage station grid connection point, determine whether frequency regulation control is required, and if necessary, adjust the output power of each device in the wind-solar-storage station.

[0347] The optimized coordination control system of wind-solar-storage station in this scheme includes:

[0348] 4.1 Data Acquisition Gateway

[0349] The data acquisition gateway is responsible for communicating with various devices within the station, collecting data such as operating status, substation information, power forecasts, power consumption, and fault recordings. It acquires data in real time through communication interfaces with the devices and integrates and transmits it using high-speed data processing technology, ensuring comprehensive and accurate data collection.

[0350] 4.2 Wind-solar-storage station coordination control device

[0351] The wind, solar, and storage station coordination control device is the core equipment for achieving optimized dispatching control. It supports two operating modes: wind, solar, and storage command control and automatic control, and has the following functional modules:

[0352] 4.2.1 Active Power Optimization Smoothing Module

[0353] This module receives power smoothing instructions from the upper layer or detects excessive fluctuations in the grid connection point. It uses the energy storage charging and discharging capabilities to smooth out wind and solar output fluctuations, thereby ensuring that the output power of each wind and solar storage station meets the grid connection requirements.

[0354] 4.2.2 Active power instruction optimization tracking module

[0355] This module receives active power commands from higher-level layers and distributes them to wind, solar, and storage stations based on optimized algorithm logic. When the current command dead zone is exceeded, it compensates for the difference between the active power command and the station's actual output, tracking the command and reducing wind and solar curtailment. Furthermore, based on short-term and ultra-short-term power forecasts from higher-level layers, the module optimizes energy storage charging and discharging times, enabling proactive energy storage operations.

[0356] 4.2.3 Primary frequency modulation module

[0357] This module supports additional control strategies, enabling primary frequency regulation at wind, solar, and storage stations. It monitors frequency deviation at the grid connection point online. When it detects a frequency deviation exceeding the primary frequency regulation dead zone, it issues active power commands to the wind, solar, and storage coordination EMS, which then distributes them to each basic controlled unit. The controlled units respond to the active power control commands, ultimately achieving primary frequency regulation at the station.

[0358] The data acquisition gateway is connected to each device in the station through a communication interface, collecting real-time data such as the equipment's operating status, substation information, power forecast information, power information, fault recording information, etc., and integrating it and uploading it to the source-grid-load-storage integrated coordination control center.

[0359] The wind, solar, and storage station coordination control device receives data uploaded by the data acquisition gateway and performs corresponding control according to the operating mode. In the wind, solar, and storage command control mode, the active power optimization and smoothing module, the active power command optimization and tracking module, and the primary frequency regulation module perform control operations according to the set logic and algorithms to achieve optimized scheduling of the wind, solar, and storage station.

[0360] The overall working principle is as follows:

[0361] 1. The data acquisition gateway obtains data such as the equipment's operating status, booster station information, power forecast information, power consumption information, and fault recording information through the communication interface with each device in the station.

[0362] 2. The data acquisition gateway integrates the collected data and uploads the data through the communication module of the source-grid-load-storage integrated coordination control center.

[0363] 3. The wind-solar-storage station coordination control device receives data uploaded by the data acquisition gateway and performs corresponding control operations according to the operating mode, such as active power optimization and smoothing, active power instruction optimization tracking and primary frequency regulation.

[0364] 4. The control device adjusts the operation strategy and power output of the wind, solar and storage station according to the optimization algorithm and logic to achieve optimized scheduling and coordinated control of the station.

[0365] Active power optimization smoothing module:

[0366] The goal of this module is to smooth out power fluctuations of wind and photovoltaic power generation through energy storage charging and discharging capabilities to meet grid connection requirements. The logic and algorithm can be shown as follows:

[0367] Step 1: Monitor the power output changes of wind and photovoltaic power generation.

[0368] Step 2: If it is detected that the power fluctuation is too large, determine whether smooth adjustment is required.

[0369] Step 3: If smooth regulation is required, calculate the required charging and discharging power based on the charging and discharging capacity of the energy storage system and the current power fluctuation.

[0370] Step 4: Control the energy storage system to perform charging and discharging operations to smooth out power fluctuations from wind and photovoltaic power generation and maintain the output power within an appropriate range.

[0371] Through the above logic and algorithms, the module can dynamically adjust the charging and discharging power of the energy storage system according to the power fluctuations of wind and photovoltaic power generation, thereby optimizing and smoothing the output power of the wind, solar and storage stations.

[0372] Active power instruction optimization tracking module:

[0373] The goal of this module is to track the active power instructions issued by the upper layer and compensate for the actual output to reduce the wind and solar power curtailment rate. The following example illustrates its logic and algorithm:

[0374] Step 1: Receive the active power command issued by the upper layer and the actual output of the current station.

[0375] Step 2: Calculate the difference (deviation) between the active power command and the actual output.

[0376] Step 3: Determine whether the current deviation exceeds the command dead zone, that is, determine whether compensation is required.

[0377] Step 4: If the deviation exceeds the instruction dead zone, calculate the compensation value according to the optimization algorithm logic.

[0378] Step 5: Control the output power of the wind, solar and storage station and adjust the actual output through the compensation value to achieve optimal tracking of the active power instruction.

[0379] Through the above logic and algorithm, the module can calculate the compensation value according to the optimization algorithm, and adjust the output power to reduce the deviation between the actual output of the wind and solar storage station and the active power instruction, thereby reducing the wind and solar power curtailment rate.

[0380] Primary frequency modulation module:

[0381] The goal of this module is to implement the primary frequency regulation function of the wind, solar and storage station, so that it can respond to frequency changes at the grid connection point. The following is an example to illustrate its logic and algorithm:

[0382] Step 1: Monitor the frequency deviation of the grid connection point online.

[0383] Step 2: Determine whether the frequency deviation exceeds the primary frequency modulation control dead zone, that is, determine whether frequency modulation control is required.

[0384] Step 3: If the frequency deviation exceeds the frequency modulation control dead zone, the active power instructions for wind, solar, and storage are calculated and adjusted according to the optimization algorithm logic.

[0385] Step 4: Control wind, solar, and energy storage to coordinate the EMS and issue active power instructions, which are further issued to each basic controlled unit, including a single wind turbine, photovoltaic inverter, and energy storage unit.

[0386] Step 5: Each basic controlled unit responds to the active power control instruction and adjusts the frequency deviation of the grid connection point by adjusting the output power, thereby achieving primary frequency regulation capability.

[0387] Through the above logic and algorithm, the module can calculate and adjust the active power instructions of wind, solar and storage according to the frequency deviation of the grid connection point, and adjust the frequency of the grid connection point by controlling the output power of each basic controlled unit, so that the wind, solar and storage station has primary frequency regulation capability.

[0388] The above solution has the following advantages:

[0389] Comprehensive and accurate data collection: Through the data collection gateway, comprehensive and accurate operating information of the station-side equipment can be obtained, providing reliable data support for dispatching control.

[0390] Flexible control strategy: The wind-solar-storage station coordinated control device supports two operating modes: wind-solar-storage command control and automatic control. It has functional modules such as active power optimization and smoothing, active power command optimization tracking and primary frequency regulation. It can be flexibly dispatched according to different scenarios and operating conditions to optimize energy utilization efficiency.

[0391] Autonomous selection of functional modules: In automatic control mode, the wind, solar and storage station can autonomously select functional modules according to the current scenario to meet specific needs and optimization goals.

[0392] Example 6

[0393] This embodiment provides a multi-source adaptive power generation coordination control system. Currently, the automatic power generation control systems on the market have the following drawbacks:

[0394] 1. Single power source control: Traditional AGC systems are mainly targeted at a single type of power source and cannot fully utilize the advantages of multiple power sources, limiting the efficiency and flexibility of power generation coordination.

[0395] 2. Traditional control strategy: Traditional AGC systems use control strategies based on fixed rules and experience. They lack adaptability and sensitivity to real-time changes in the system and cannot effectively deal with complex dynamic balance issues of power supply and demand.

[0396] 3. Data processing complexity: Traditional systems require a large amount of complex data processing and calculations, resulting in slow system response and high operating costs.

[0397] To solve these problems, this scheme proposes a multi-source adaptive power generation coordinated control system, which realizes the adaptability and flexibility of the power generation process through innovative algorithms, optimization methods and strategies.

[0398] The automatic power generation control system currently on the market has the following defects:

[0399] 1. Single power source control: Traditional AGC systems are mainly targeted at a single type of power source and cannot fully utilize the advantages of multiple power sources, limiting the efficiency and flexibility of power generation coordination.

[0400] 2. Traditional control strategy: Traditional AGC systems use control strategies based on fixed rules and experience. They lack adaptability and sensitivity to real-time changes in the system and cannot effectively deal with complex dynamic balance issues of power supply and demand.

[0401] 3. Data processing complexity: Traditional systems require a large amount of complex data processing and calculations, resulting in slow system response and high operating costs.

[0402] To solve these problems, this scheme proposes a multi-source adaptive power generation coordinated control system, which realizes the adaptability and flexibility of the power generation process through innovative algorithms, optimization methods and strategies.

[0403] The multi-source adaptive power generation coordinated control method comprises the following steps:

[0404] Obtain status data of each power generation equipment in the power grid;

[0405] Federated learning is used to centrally train the status data of each power generation device to obtain a global power generation prediction model. The obtained global power generation prediction model is combined with the physical model of the corresponding power generation device to obtain an overall prediction model.

[0406] According to the real-time status data and optimization objectives of each power generation device, the power generation control strategy and parameters of the overall prediction model are dynamically adjusted, and the control strategy of each power generation device is obtained using the adjusted overall prediction model.

[0407] Specific plans include:

[0408] 4.1 Data Collection and Processing

[0409] The automatic power generation control system first collects real-time status data from the power generation equipment, including parameters such as current, voltage, and frequency, through monitoring equipment and sensors connected to the equipment. This data undergoes preprocessing, cleaning, and feature extraction to obtain an accurate data foundation to support subsequent control and optimization.

[0410] 4.2 Multi-source adaptive power generation coordinated control algorithm

[0411] This solution designs an innovative multi-source adaptive generation coordination control algorithm that combines the concepts of federated learning and data-physical fusion. The algorithm first establishes a federated learning model. Through this method, data distributed across different power generation devices are centrally trained to obtain a global power generation prediction model. Then, using data-physical fusion technology, the physical and data models are combined to predict and optimize power generation, taking into account actual operating conditions and historical data.

[0412] 4.3 Adaptive Optimization Strategy

[0413] The system employs an adaptive optimization strategy, automatically adjusting power generation control strategies and parameters based on real-time monitoring data and optimization objectives. Based on the real-time demands and stability requirements of the power generation system, the system dynamically adjusts power distribution and regulation strategies according to optimization objectives and constraints to achieve a balance between system frequency and net exchange power. This strategy utilizes an iterative optimization algorithm, continuously adjusting and optimizing based on actual operating conditions to improve system performance and efficiency.

[0414] Specific control methods include:

[0415] Step 1: Data collection and preprocessing

[0416] By connecting to monitoring equipment and sensors, the system collects real-time status data of power generation equipment, including parameters such as current, voltage, and frequency. The collected data undergoes preprocessing, cleaning, and feature extraction to obtain accurate data input.

[0417] Step 2: Multi-source adaptive generation coordinated control algorithm

[0418] Based on the collected data, a multi-source adaptive power generation coordinated control algorithm is applied. This algorithm first establishes a federated learning model, centrally training data distributed across various power generation devices to obtain a global power generation prediction model. Then, using data-physics fusion technology, the physical and data models are combined, taking into account actual operating conditions and historical data to predict and optimize power generation.

[0419] Step 3: Adaptive Optimization Strategy and Adjustment

[0420] Based on real-time monitoring data and optimization objectives, the system employs an adaptive optimization strategy. Based on the real-time needs and stability requirements of the power generation system, the system dynamically adjusts power distribution and regulation strategies to achieve a balance between system frequency and net exchange power. The system employs an iterative optimization algorithm, adjusting and optimizing based on actual operating conditions to improve system performance and efficiency.

[0421] The automatic power generation control system has the following advantages:

[0422] 1. Efficiency: Through innovative algorithms and optimization strategies, we achieve multi-source adaptive power generation coordinated control, improving the efficiency and performance of the power generation system. The system automatically adjusts power distribution and regulation strategies based on real-time demand and optimization objectives to achieve a real-time balance between power supply and demand.

[0423] 2. Accuracy: Utilizing data acquisition and preprocessing technologies, we obtain accurate power generation equipment status data and use multi-source coordinated control algorithms to predict power generation. The system comprehensively considers physical models and historical data to provide precise power generation forecasts to meet power supply and demand requirements.

[0424] 3. Adaptability: The system employs an adaptive optimization strategy, dynamically adjusting power generation control strategies and parameters based on real-time monitoring data and optimization objectives. The system automatically adjusts power distribution and regulation strategies to maintain system frequency and net exchange power within acceptable ranges, tailored to varying operating conditions and requirements.

[0425] Example 7

[0426] This embodiment provides a composite allocation method with the goal of optimizing efficiency. Currently, there are some technical deficiencies in multi-power and multi-load cross-optimization, such as:

[0427] 1. Traditional allocation strategies are relatively simple and fail to fully consider the cross-influence of multiple factors, resulting in inflexible and inefficient energy allocation.

[0428] 2. Some solutions lack comprehensive optimization of different load demands, resulting in low energy utilization efficiency.

[0429] Some solutions have difficulty in applying to complex systems and cannot handle large-scale cross-optimization problems between power sources and loads.

[0430] Several relevant papers and patents have been published in this area. For example, some papers have proposed a genetic algorithm-based method for optimizing power system energy distribution, and some patents have proposed a multi-source, multi-load coordinated control system based on fuzzy logic. However, these solutions still have limitations and cannot fully address the challenges of cross-optimization of multiple sources and loads in complex power systems.

[0431] Compared with existing solutions, the present invention provides an innovative composite distribution method and system, which can better solve the multi-power and multi-load cross-optimization problems, and improve energy utilization efficiency and system operation effect.

[0432] The purpose of this solution is to solve the problems existing in the cross-optimization of multiple power sources and multiple loads. By designing a composite distribution strategy, it aims to achieve efficient energy distribution among multiple power sources and loads in the power system, optimize system operation efficiency, and improve energy utilization efficiency.

[0433] This method includes the following steps:

[0434] Based on real-time data from the power system, a composite allocation algorithm is used to select the optimal energy allocation plan for each power generation equipment and load. The composite allocation algorithm is composed of a combination of multiple optimization strategies;

[0435] According to the optimal energy distribution plan, corresponding control instructions are generated to control and adjust each power generation equipment and load.

[0436] This solution system includes the following main components / parts:

[0437] a) Data acquisition unit: used to collect various data in the power system, including power generation capacity, load demand, energy prices and other information.

[0438] b) Composite distribution algorithm module: It adopts an innovative composite distribution algorithm, combined with multiple optimization strategies and models, to perform multi-power and multi-load cross-optimization energy distribution.

[0439] c) Allocation decision unit: Based on the results of the composite allocation algorithm, it makes the final energy allocation decision and determines the energy allocation plan between the power source and the load.

[0440] d) Control execution unit: converts allocation decisions into actual control instructions to control and regulate power sources and loads in the power system.

[0441] The connections and logical relationships between the various components / parts are as follows:

[0442] 1. The data acquisition unit collects various data in the power system through sensors and other equipment, and transmits the data to the composite distribution algorithm module.

[0443] 2. The composite distribution algorithm module uses the collected data, applies an innovative composite distribution algorithm, and combines multiple optimization strategies and models to perform energy distribution calculations for multi-power and multi-load cross-optimization to obtain the optimal energy distribution plan.

[0444] 3. The allocation decision unit receives the calculation results of the composite allocation algorithm module and makes the final energy allocation decision based on the system's operating requirements, load demand and energy supply.

[0445] 4. The control execution unit converts the energy allocation decision into actual control instructions according to the instructions of the allocation decision unit, and controls and adjusts the power supply and load in the power system through control equipment to achieve optimal energy distribution.

[0446] Through the above connections and logical relationships, the entire system can achieve efficient optimization of energy distribution between multiple power sources and loads, and realize dynamic energy distribution adjustment according to system requirements.

[0447] As a specific example of the composite allocation strategy, we can introduce a preferred algorithm, namely the Genetic Algorithm (GA), for energy allocation with multi-power sources and multi-load cross optimization.

[0448] A genetic algorithm is an optimization algorithm that simulates natural evolutionary processes. It seeks the optimal solution to a problem by simulating natural processes such as inheritance, crossover, and mutation. In a composite allocation strategy, a genetic algorithm can be used to optimize energy allocation to achieve efficient energy utilization in the system.

[0449] The following is the workflow of the genetic algorithm in the composite allocation strategy:

[0450] 1. Initialize the population:

[0451] Population size: Set the number of individuals in the population, for example, 100 solutions as the initial population.

[0452] Solution representation: Each solution is represented by a set of genes, each gene represents the energy distribution ratio of the power source or load.

[0453] Gene Length: Determines the number of bits per gene and is usually related to the number of power supplies or loads.

[0454] 2. Fitness evaluation:

[0455] Fitness function: Design a fitness function to evaluate the quality of each solution. The fitness function can take into account factors such as energy efficiency, energy waste, and system stability.

[0456] Objective function weights: Set weights for different objectives to guide the algorithm to balance between multiple objectives.

[0457] 3. Select an action:

[0458] Selection Operator Type: Select an appropriate selection operator, such as Roulette Selection or Tournament Selection.

[0459] Selection pressure: controls the number of solutions retained in the selection operation to influence the diversity of solutions in the next generation.

[0460] 4. Crossover operation:

[0461] Crossover probability: Set the probability of the crossover operation to control the frequency of crossover of gene segments in the parent solution.

[0462] Crossover mode: Select an appropriate crossover mode, such as single-point crossover, multi-point crossover, or uniform crossover.

[0463] 5. Mutation operation:

[0464] Mutation probability: Determines the probability that a mutation operation will occur to introduce random changes to a gene.

[0465] Mutation mode: Select an appropriate mutation mode, such as position mutation or gene exchange mutation.

[0466] 6. Update population:

[0467] Elite strategy: Determine whether to retain the solution with the best fitness in the previous generation as the elite and pass it directly to the next generation to maintain the excellence of the population.

[0468] Reproduction strategy: Determines how to combine parent solutions and offspring solutions to construct a new population.

[0469] 7. Termination condition judgment:

[0470] Maximum number of iterations: Set the maximum number of iterations of the algorithm. When this number is reached, the evolution process will be terminated.

[0471] Fitness threshold: When the fitness reaches a certain threshold, it is considered that the optimal solution has been reached and the algorithm can be terminated early.

[0472] Through the iterative evolution process of the genetic algorithm, the composite allocation strategy can search for energy allocation solutions with higher fitness, realize multi-power source and multi-load cross-optimization, and thus achieve the goal of efficient energy utilization.

[0473] The composite allocation strategy in the present invention combines genetic algorithms with other optimization strategies, fully considers the cross-influence of multiple factors, has flexibility, adaptability and scalability, can optimize energy distribution schemes, improve energy utilization efficiency and system operation effects.

[0474] This solution has the following advantages:

[0475] 1. Innovative composite allocation strategy: The innovative composite allocation algorithm can fully consider the cross-influence of multiple factors and achieve efficient energy distribution with cross-optimization of multiple power sources and multiple loads.

[0476] 2. Efficient energy utilization: By optimizing the energy distribution plan, efficient energy utilization of the system can be achieved, reducing energy waste and costs.

[0477] 3. Flexibility and adaptability: The solution can flexibly adjust energy allocation strategies based on system requirements and real-time conditions to adapt to different load demands and power supply changes.

[0478] 4. System operation optimization: By optimizing energy distribution, the system operation efficiency and stability can be improved, and the system energy consumption and loss can be reduced.

[0479] 5. Scalability and applicability: The solution is applicable to power systems of various sizes and types and has strong scalability and adaptability.

[0480] Example 8

[0481] This embodiment provides a multi-energy emergency machine-grid coordination system. Current solutions on the market have the following drawbacks:

[0482] 1. The lack of a wide-area dynamic synchronous monitoring system across the entire network makes it impossible to conduct high-speed synchronous dynamic monitoring and alarms for various disturbances and faults.

[0483] 2. The control system lacks the ability to quickly coordinate control based on the characteristics of different types of controlled power sources, and is unable to automatically adjust the grid frequency and voltage in a short period of time.

[0484] 3. When a large power generation loss or downstream load failure occurs on the power generation side, there is a lack of a fast balancing stabilization system, which makes it impossible to quickly cut off the downstream load or quickly reduce the output of the generator set.

[0485] This solution aims to address the rapid response and coordinated control issues faced by power systems in emergency situations. By configuring a multi-energy emergency machine-grid coordination system, it enables wide-area dynamic synchronous monitoring, rapid coordinated control, and system stability. This ensures the safe and stable operation of the power system in emergency situations, mitigates the adverse impact of power source or load failures on the grid, and achieves rapid balance between power generation and consumption.

[0486] The advantages of the present invention are:

[0487] 1. By configuring a wide-area dynamic synchronous monitoring system, high-speed synchronous dynamic monitoring, recording and alarming of gas turbines, wind power, photovoltaic power, loads and power grids across the entire network can be achieved, including early judgment, positioning and alarming of hidden faults, thereby avoiding the expansion and penetration of faults.

[0488] 2. The equipment has a fast coordinated control system tailored to the characteristics of different types of controlled power sources, capable of achieving a 10-millisecond response capability for photovoltaic and wind power generation, and automatically controlling the grid frequency and voltage when the enterprise power grid operates independently, including control of plant power island operation after full load shedding.

[0489] 3. The stabilization and control system can quickly cut off downstream loads or quickly reduce the output of generator sets to ensure a rapid balance between power generation and consumption.

[0490] This program includes:

[0491] Wide-area dynamic synchronous monitoring system for synchronous dynamic monitoring of transient disturbances and faults in energy systems;

[0492] Rapid collaborative control system, used for rapid response and collaborative control of different types of power generation equipment in the energy system;

[0493] Grid stability control system, used to stabilize and regulate the grid of the energy system;

[0494] The energy storage frequency stabilization cooperative control system is used to achieve frequency stabilization and coordinated control of the energy storage system.

[0495] As shown in FIG5 , specifically,

[0496] 1. Wide-area dynamic synchronous monitoring system includes:

[0497] PMU synchronized phasor measurement device;

[0498] DCS unit power and thermal dynamic data acquisition equipment;

[0499] CT, PT power grid and load dynamic data acquisition equipment;

[0500] 2. Rapid collaborative control system includes:

[0501] Fast coordinated control strategy cabinet;

[0502] Unit cooperative control execution cabinet;

[0503] Photovoltaic coordinated control execution cabinet;

[0504] Unit speed control system;

[0505] Excitation controller;

[0506] Photovoltaic inverters;

[0507] 3. The grid stability control system includes:

[0508] Main station for stabilization and control strategies;

[0509] Stable control execution substation;

[0510] Cuttable units;

[0511] load shedding;

[0512] Chaifa;

[0513] 4. The energy storage frequency stabilization coordination control system includes:

[0514] Energy storage balancing execution cabinet;

[0515] Energy storage PCS control equipment.

[0516] The specific functions correspond to the following:

[0517] 1. Wide-area dynamic synchronous monitoring system:

[0518] The wide-area dynamic synchronous monitoring system is an important component of the multi-energy emergency machine-grid coordination system. Its main function is to achieve high-speed synchronous dynamic monitoring, recording, and alarming of transient disturbances and faults across the entire network. The system consists of the following components:

[0519] PMU synchronous phasor measurement device: Through the PMU device installed at the key node, the voltage, current and phase angle and other synchronous phasor information of each node in the power system are collected in real time and transmitted to the wide-area dynamic synchronous monitoring system in a high-speed synchronous manner.

[0520] DCS unit power and thermal dynamic data acquisition equipment: By collecting the unit power and thermal dynamic data, the real-time operating status of the unit can be obtained, providing data support for subsequent rapid collaborative control.

[0521] CT, PT power grid and load dynamic data acquisition equipment: By collecting dynamic data of the power grid and load, including current, voltage, power and other parameters, it can monitor the status changes of the power grid and load in real time and compare and analyze them with PMU data.

[0522] Through the coordinated work of these devices, the wide-area dynamic synchronous monitoring system can perform high-speed synchronous dynamic monitoring, recording and alarm of various transient disturbances and faults in the power system, ensuring the safety and stability of system operation.

[0523] 2. Rapid collaborative control system:

[0524] The rapid coordinated control system is the core component of the multi-energy emergency machine-grid coordination system. Its main function is to achieve rapid response and coordinated control of different types of controlled power sources. The system includes the following components:

[0525] Fast collaborative control strategy cabinet: As the central control unit, the strategy cabinet is responsible for formulating and executing fast collaborative control strategies, coordinating the operating status of each subsystem according to system requirements and optimization goals.

[0526] Generator Coordination Execution Cabinet: This cabinet connects the generator speed control system and excitation controller to achieve coordinated control of the generator set. Based on the system's operating status and coordination strategy, it adjusts the generator set's load output, speed regulation performance, and excitation current to achieve rapid response and coordinated control of the generator set.

[0527] Photovoltaic Coordinated Control Execution Cabinet: This cabinet connects to PV inverters to achieve coordinated control of PV power generation. Based on the system's operating status and coordination strategy, it adjusts the inverter's output power and voltage to achieve rapid response and coordinated control of PV power generation.

[0528] The various components of the rapid collaborative control system achieve rapid response and collaborative control of different types of controlled power sources through data interaction and collaborative work, thereby improving the rapid response capabilities of photovoltaic, wind power and other power generation, and maintaining the frequency and voltage stability of the power grid.

[0529] 3. Grid stability control system:

[0530] The grid stability control system is an important component of the multi-energy emergency machine-grid coordination system. Its main function is to achieve stable control and regulation of the power grid. The system consists of the following components:

[0531] Stability control strategy master station: As the central control unit, the master station is responsible for formulating and implementing grid stability control strategies, and adjusting grid parameters such as frequency, voltage, and power according to the grid operating status and load demand.

[0532] Stability Control Execution Substation: This substation connects switchable units, switchable loads, and diesel generators to achieve stable control and regulation of the power grid. Based on the stability control strategy and operational requirements, the substation controls the load output and switching status of switchable units, regulates the connection and disconnection of switchable loads, and controls the start and stop of diesel generators and their power regulation.

[0533] The grid stability control system can achieve stable control and regulation of the grid through the collaborative work between the strategy master station and the execution substation, ensuring the operational stability and supply and demand balance of the grid.

[0534] 4. Energy storage frequency stabilization cooperative control system:

[0535] The energy storage frequency stabilization and coordinated control system primarily consists of an energy storage balancing executive cabinet, which, through connection to the energy storage PCS control equipment, achieves frequency stabilization and coordinated control of the energy storage. The energy storage balancing executive cabinet adjusts the charge and discharge power of the energy storage based on the system's operating status and energy storage requirements, achieving stable frequency regulation and coordinated control.

[0536] Through the connection and collaborative work between the above components, the multi-energy emergency machine-grid coordination system can achieve rapid coordinated control and management of the power system, ensuring the stable operation and balanced regulation of the power grid.

[0537] The advantages of this solution are mainly reflected in its structure and function. The specific advantages are as follows:

[0538] 1. Structural advantages:

[0539] Reasonable structure: The architecture design of the multi-energy emergency machine-grid coordination system is reasonable, adopting a hierarchical structure of master station and subsystems to ensure the collaborative work and information interaction between various components, making the system operation more efficient and stable.

[0540] Modular design: The system adopts a modular design, with independence and scalability between different subsystems, which facilitates system installation, maintenance and upgrades, and improves system flexibility and reliability.

[0541] 2. Functional advantages:

[0542] Rapid response capability: The system has rapid response capability through rapid coordinated control and monitoring systems. It can quickly make corresponding adjustments when emergencies or failures occur in the power system to maintain stable operation of the system.

[0543] Efficient energy management: The system can monitor and control the power generation and load of multiple energy sources in real time. Through optimized scheduling and coordinated control, it can achieve efficient energy utilization and balance supply and demand, thereby improving energy utilization efficiency.

[0544] Improve power supply reliability: Through functions such as wide-area dynamic synchronous monitoring and grid stability control, the system can quickly detect and identify faults and disturbances in the power system and take corresponding measures to ensure power supply reliability and stable operation of the grid.

[0545] Frequency and voltage stability: The system uses the energy storage frequency stability coordination system and the grid stability control system to adjust and control the frequency and voltage of the grid in real time, maintain grid stability, and avoid the impact of frequency and voltage fluctuations.

[0546] Example 9

[0547] This embodiment provides an automated intelligent power supply network reconstruction method and system. Current power supply network reconstruction solutions on the market have the following drawbacks:

[0548] 1. Long reconstruction time: Traditional power supply network reconstruction methods require manual inspection and adjustment of network topology, which is time-consuming and affects the speed of power supply restoration.

[0549] 2. Extensive manual intervention: Existing solutions require a lot of manual intervention and decision-making, are easily affected by human factors, and increase operational risks.

[0550] 3. Lack of automation: Some solutions lack automation capabilities and cannot respond quickly to failures and changing situations.

[0551] To solve these problems, this solution proposes a power supply network rapid reconstruction system, which realizes rapid reconstruction and fault handling of the power supply network through automated and intelligent methods.

[0552] The purpose of this solution is to provide a fast and automated power network reconstruction system to address the shortcomings of existing solutions. Its advantages include:

[0553] 1. Rapid Reconfiguration: Introducing innovative algorithms and optimization models that can quickly detect fault points and anomalies in the power supply network and automatically reconfigure the network topology.

[0554] 2. Automated operation: This solution implements automated operation of power supply network reconstruction, reducing the need for manual intervention and decision-making, and improving the accuracy and efficiency of operations.

[0555] 3. Intelligent decision-making: By introducing intelligent algorithms and machine learning technologies, this solution can automatically analyze and determine the status of the power supply network, make corresponding decisions, and optimize power restoration strategies.

[0556] 4. Flexibility and adaptability: This solution is flexible and adaptable, able to adapt to power supply networks of different sizes and complexities, and can be flexibly adjusted and optimized according to actual conditions.

[0557] This program includes:

[0558] Obtain status data of the power supply network in the energy system and perform network topology analysis and fault diagnosis based on the status data; if a power supply network failure occurs, obtain a power supply network reconstruction plan based on the preset power supply optimization strategy;

[0559] The power supply network is topologically reconfigured according to the power supply network reconstruction plan.

[0560] Specifically include:

[0561] 4.1 Data collection and processing:

[0562] This solution uses monitoring equipment and sensors connected to the power supply network to collect real-time data on the network's status, including parameters such as current, voltage, and frequency. The collected data is preprocessed and cleaned to provide accurate basic data for subsequent network reconstruction and decision-making.

[0563] 4.2 Network topology detection and analysis:

[0564] Based on the collected data, this solution uses innovative algorithms and models to detect and analyze the power supply network topology. By analyzing the power flow and voltage changes between nodes, it can identify fault points, load anomalies, and other situations, and reconstruct the network topology.

[0565] 4.3 Reconstruction decision and optimization:

[0566] Based on the results of topology analysis, this solution utilizes an intelligent decision-making model to automatically determine reconstruction strategies and restoration plans. Based on the actual power supply network conditions and optimization goals, it determines appropriate disconnection and reconnection operations to minimize power outages and ensure power transmission reliability.

[0567] 4.4 Automatic Reconstruction and Monitoring:

[0568] This solution enables automatic reconfiguration of the power supply network, implementing network topology changes and node reconnection through an automated control system. Simultaneously, the system monitors the reconfigured network in real time to ensure stable operation and timely troubleshooting.

[0569] The working principle of this solution is based on an automated process of data collection, analysis and decision-making to achieve rapid reconstruction of the power supply network. The optimization principle includes the following aspects:

[0570] 5.1 Data Collection and Processing

[0571] First, the system collects real-time data on the power supply network's status, including parameters such as current, voltage, and frequency, by connecting to monitoring devices and sensors connected to the network. This data is pre-processed and cleaned to ensure accuracy and usability.

[0572] 5.2 Network Topology Analysis

[0573] Based on the collected power supply network status data, the system performs network topology analysis. By analyzing information such as power flow and voltage changes between nodes, the system can identify fault points, load anomalies, and power transmission bottlenecks in the power supply network.

[0574] 5.3 Fault diagnosis and decision making

[0575] Based on the results of network topology analysis, the system performs fault diagnosis and decision-making. Using advanced algorithms and models, the system automatically identifies the type and location of the fault and generates a corresponding fault report. Based on the fault report and network status information, the system employs an intelligent decision-making module to develop a power supply network reconstruction plan based on pre-set optimization goals and strategies.

[0576] 5.4 Network Reconfiguration and Operation

[0577] The system automatically reconfigures the network and performs operations based on the established reconfiguration plan. This includes disconnecting affected nodes, adjusting line connections, and reconfiguring transformers. Through automated control systems, the system can implement network topology changes and node reconnections, enabling the reconfiguration of the power supply network.

[0578] 5.5 Real-time monitoring and feedback

[0579] After the network reconstruction is complete, the system provides real-time monitoring and feedback. By connecting to monitoring devices and sensors, the system continuously monitors the power supply network's status data and compares and analyzes it with pre-reconstruction data. If any anomalies or faults recur, the system immediately issues an alert and automatically initiates further processing and adjustments.

[0580] 5.6 Optimization and Self-Learning

[0581] The system is capable of optimization and self-learning. Based on actual operating conditions and feedback from network reconstruction, it continuously optimizes and adjusts reconstruction strategies and parameter settings to improve system performance and accuracy. Furthermore, the system can self-learn based on historical data and operational experience, enhancing its understanding and predictive capabilities of the power supply network.

[0582] Through the above workflow, this power supply network rapid reconstruction system can automatically identify faults and abnormal conditions in the power supply network, and formulate a rapid reconstruction plan to achieve rapid recovery and stable operation of the power supply network.

[0583] The innovation of this solution lies in the introduction of automated and intelligent methods to achieve rapid reconstruction and fault handling of the power supply network. The specific advantages and innovations are as follows:

[0584] 1. Rapid response: Through automated processes and intelligent decision-making models, the power supply network can be quickly reconfigured and restored, shortening power outages.

[0585] 2. Automated operation: Reduces the need for manual intervention and decision-making, and reduces operational risks and the impact of human factors.

[0586] 3. Intelligent decision-making: By introducing intelligent algorithms and machine learning technologies, reasonable decisions are made and reconstruction strategies are optimized based on the actual situation of the power supply network and optimization goals.

[0587] 4. Flexibility and adaptability: The system must be able to adapt to power supply networks of varying sizes and complexities, and be flexibly adjusted and optimized based on actual conditions.

[0588] Example 10

[0589] This embodiment provides an isolated grid stability control system and method based on five lines of defense. To address the shortcomings of similar solutions currently on the market, in large power grids, to ensure safe and stable grid operation and avoid large-scale power outages, the "Guidelines for Power System Safety and Stability" proposes the concept of three lines of defense for power systems, as shown in Figure 6. For isolated grids with a high proportion of renewable energy, since power electronic renewable energy sources such as wind power and photovoltaics lack rotational inertia and fast-response energy storage, large disturbances such as N-1 faults or abnormal load startup shocks may cause frequency over-limits, triggering the stabilization device to operate, causing generator and load shedding, and reducing power supply reliability and stability. Relying on traditional second-level automatic control (AGC) is difficult to maintain stable operation of a grid with a high proportion of renewable energy, resulting in significant frequency fluctuations. It is necessary to improve the rapid response capabilities of photovoltaic, wind power, and energy storage to quickly achieve power generation and supply balance, avoid frequent and large frequency fluctuations, and thus avoid triggering generator and load shedding, which are the second or third lines of defense of the regional stability system.

[0590] Currently, the market generally adopts the three-line defense solution for power systems. However, the three-line defense solution cannot cover all operating conditions of isolated power grid systems and has the following defects:

[0591] 1. Lack of effective solutions for isolated grid operation with a high proportion of new energy.

[0592] 2. Traditional second-level AGC is difficult to maintain stable operation of a power grid with a high proportion of new energy.

[0593] 3. New power electronic energy sources such as wind power and photovoltaics lack rotational inertia and fast-response energy storage, resulting in large frequency fluctuations.

[0594] The purpose of this solution is to solve the above problems and it has the following advantages:

[0595] 1. Achieved stable control of isolated grids with a high proportion of new energy, improving the reliability and stability of the power grid.

[0596] 2. Improve rapid response capabilities to avoid frequent and large frequency fluctuations.

[0597] 3. Realize coordinated control of sources, grids, loads and storage through emergency coordinated control systems to ensure stable operation of the power grid.

[0598] As shown in Figure 7, this solution includes the following components and parts:

[0599] Line of Defense 1: Reasonable Component Protection

[0600] Within 100ms of a fault occurring, high-speed relays and protection devices proactively isolate the faulty portion of the grid based on fault identification. Properly configured component protection quickly isolates the fault, preventing its spread and improving grid reliability and stability.

[0601] Line of Defense 2: Power Supply Network Rapid Reconfiguration System

[0602] Within 10ms of a power grid island, the power supply network rapid reconstruction system swiftly activates, restoring power to the outaged loads without interrupting operation. This system monitors the grid topology and, based on pre-designed restoration paths, controls rapid closing operations to maintain grid connectivity and integrity. By rapidly reconfiguring the power supply network, power can be quickly restored to the outaged loads, minimizing the scope of the outage and improving grid reliability.

[0603] Defense Line 3: Network-wide emergency machine-network coordination control system

[0604] Within 200 milliseconds of a power isolation event, the grid-wide emergency generator-grid coordination and control system plays a key role. Through rapid power and frequency control measures, the system restores power generation and load balance, maintaining safe main steam pressure. Before significant frequency and voltage deviations occur, it controls generator output and load adjustments to achieve rapid power balance and frequency restoration. This approach prevents frequent and significant frequency fluctuations and improves grid stability.

[0605] Defense Line 4: Low-frequency and low-voltage load reduction and high-frequency generator cutting control

[0606] This defense line is activated when emergency grid-stabilizing coordinated measures, such as joint generator-cutoff, fail to limit the isolated grid frequency to a safe range. Low-frequency and low-voltage load shedding and high-frequency generator shedding control restore deteriorating frequency and voltage to a safe range. Low-frequency and low-voltage load shedding primarily reduces load consumption to lower frequency and voltage, while high-frequency generator shedding controls frequency and voltage recovery by partially removing load. These two control measures, combined, effectively limit frequency and voltage excursions and maintain grid stability.

[0607] Line of Defense 5: Minimum Power Generation System

[0608] If the last line of defense for stabilization still fails to maintain grid stability, the minimum generation system is activated. This system divides the grid into the smallest system with sufficient generating capacity, providing power for the automatic recovery of the enterprise grid and maintaining the most basic critical loads. By selecting appropriate generator sets, the minimum generation system maintains basic grid operation at the lowest possible capacity, ensuring power supply to critical loads and supporting grid recovery.

[0609] This solution has the following advantages:

[0610] 1. Realize stable control of isolated grids with a high proportion of new energy and improve the reliability and stability of the power grid.

[0611] 2. Improve rapid response capabilities to avoid frequent and large frequency fluctuations.

[0612] 3. Adopt emergency coordinated control system to realize coordinated control of source, grid, load and storage.

[0613] 4. Provides comprehensive adjustment and protection measures to cope with various possible isolated grid conditions.

[0614] 5. By setting up five lines of defense, a complete and strong defense system has been built.

[0615] Example 11

[0616] This embodiment provides an intelligent unmanned operation system and method thereof. Current similar solutions have some defects, such as:

[0617] 1. Lack of intelligent analysis capabilities: Existing solutions are limited in data collection and analysis and cannot provide intelligent analysis and operational reporting functions.

[0618] 2. Unstable remote control: Existing solutions have problems with transmission delays and unstable connections in remote control, making it impossible to achieve efficient unmanned operations.

[0619] 3. Complex system integration: The various components in the existing solution lack close integration and collaboration, resulting in high complexity in system integration and operation.

[0620] Existing literature and patents have solved some of the problems, but there are the following differences compared with this solution:

[0621] 1. Intelligent analysis host: This solution introduces an intelligent analysis host that can perform intelligent analysis on the collected data to generate inspection results and unmanned operation reports.

[0622] 2. Real-time monitoring and intelligent linkage: This solution has real-time monitoring capabilities and realizes intelligent linkage with the main and auxiliary equipment monitoring systems, which can better grasp the equipment status and environmental data, and improve operational efficiency and safety.

[0623] The purpose of this solution is to solve the problems of existing solutions in terms of intelligent analysis capabilities, remote control stability, and system integration complexity. Its main goals include:

[0624] 1. Realize intelligent analysis of unmanned operation tasks of substations and generate inspection results and unmanned operation reports.

[0625] 2. Provide stable remote control capabilities to support efficient unmanned operations.

[0626] 3. Achieve tight integration and collaboration between system components to simplify system integration and operation.

[0627] As shown in Figure 8, this solution includes:

[0628] 4.1 Unmanned Operation Host: Responsible for issuing control instructions and tasks, receiving data and files, and realizing remote control and data management functions.

[0629] 4.2 Intelligent Analysis Host: Used to perform intelligent analysis on the collected data to generate inspection results and unmanned operation reports.

[0630] 4.3 Track-mounted robot: used for joint unmanned operation of indoor and outdoor equipment, executes instructions issued by the unmanned operation host, collects data and files, and uploads them to the unmanned operation host.

[0631] 4.4 Camera: used for monitoring and recording indoor and outdoor equipment.

[0632] Other interface equipment: including voiceprint monitoring devices, main and auxiliary equipment monitoring systems, etc.

[0633] The connection relationship and working principle of the unmanned operation host and other components:

[0634] a) Interface with the Robot Patrol System: The unmanned operation host communicates with the robot patrol system via the TCP transport protocol. It issues control commands and unmanned operation tasks to the robot and receives unmanned operation data and status information from the robot. Furthermore, using secure file transfer protocols such as FTPS, the unmanned operation host can receive files such as visible light photos and infrared images collected by the robot.

[0635] b) Interface with the video system: The unmanned operation host communicates with the hard disk recorder in the video system through the TCP / UDP transmission protocol. It can obtain the video and infrared spectrum data of the camera and realize the control of the camera.

[0636] c) Interface with the voiceprint monitoring device: The unmanned operation host communicates with the voiceprint monitoring device through the TCP / UDP transmission protocol to obtain sound monitoring data.

[0637] d) Interface with the primary and auxiliary equipment monitoring system: The unmanned operation host communicates with the primary and auxiliary equipment monitoring system through the forward and reverse isolation devices between Zones II and IV. This communication uses the UDP protocol and CIM / E language format to achieve intelligent linkage and information exchange between the unmanned operation system and the primary and auxiliary equipment monitoring system.

[0638] e) Interface with the Intelligent Analysis Host: Communication between the unmanned operation host and the intelligent analysis host occurs via the TCP transport protocol. The unmanned operation host sends identification and analysis task instructions to the intelligent analysis host and receives the identification and analysis results. The file transfer interface uses the FTPS protocol for file transfer.

[0639] f) Interface with the Superior System: The unmanned operation host communicates with the superior system via the TCP protocol. It transmits commands for task management, remote control, model synchronization, and other tasks. The video transmission interface complies with the Q / GDW 1517.1 Interface B protocol, and the file transfer interface uses the FTPS protocol.

[0640] The workflow of the entire unmanned operation system is as follows:

[0641] 1. Initialization phase:

[0642] Start the unmanned operation host and intelligent analysis host, and establish connections with other components.

[0643] Perform system self-test and equipment calibration to ensure that all components are functioning normally.

[0644] 2. Instruction issuance stage:

[0645] The unmanned operation host receives instructions from the superior system or operators, including unmanned operation tasks, control instructions and analysis tasks.

[0646] The unmanned operation host sends instructions to the track-mounted robot, camera and other interface devices through the corresponding interface.

[0647] 3. Equipment operation stage:

[0648] The track-mounted robot executes the received unmanned operation task instructions and performs operations such as equipment inspection, data collection and document shooting.

[0649] The camera monitors and shoots the equipment, and obtains data such as video and infrared images.

[0650] 4. Data collection and transmission stage:

[0651] The rail-mounted robot collects information such as equipment status, environmental data, and files.

[0652] The collected data and files are transmitted to the unmanned operation host through the corresponding interface for subsequent processing and storage.

[0653] 5. Data analysis phase:

[0654] The unmanned operation host transmits the collected data to the intelligent analysis host.

[0655] The intelligent analysis host performs intelligent analysis and processing on the data to generate inspection results and unmanned operation reports.

[0656] 6. Result reporting and alarm stage:

[0657] The unmanned operation host receives the inspection results and unmanned operation reports generated by the intelligent analysis host.

[0658] According to the set conditions and rules, timely send alarm information to relevant personnel or systems.

[0659] 7. Real-time monitoring and linkage control stage:

[0660] The unmanned operation host conducts real-time monitoring and data exchange with the video system to obtain the video and infrared images of the camera.

[0661] Data is exchanged with the voiceprint monitoring device and the main and auxiliary equipment monitoring systems to achieve status monitoring and intelligent linkage control.

[0662] 8. System maintenance and update phase:

[0663] Regularly maintain and inspect the unmanned operation system to ensure the normal operation of the equipment.

[0664] Update software and algorithms as needed to improve system performance and functionality.

[0665] The entire unmanned operation system workflow encompasses the entire process, from command issuance, equipment operation, data collection and transmission, data analysis, to result reporting and alarms. The system also provides real-time monitoring and coordinated control capabilities to ensure normal equipment operation and timely response to abnormal situations. System maintenance and updates ensure system stability and continuous improvement.

[0666] This solution has the following advantages:

[0667] High system integration: This solution utilizes multiple components, including an intelligent unmanned operation host, a track-mounted robot, and cameras, all tightly integrated and coordinated through various interfaces. This highly integrated system design simplifies deployment and operation, improving overall system efficiency and stability.

[0668] Strong intelligent analysis capabilities: This solution introduces an intelligent analysis host, which uses advanced algorithms and artificial intelligence technology to intelligently analyze and process collected data. Compared with traditional solutions, the introduction of intelligent analysis capabilities enables the system to achieve higher data utilization value and operational decision-making capabilities.

[0669] Multifunctional Support: In addition to equipment inspection and data collection, this solution also supports document capture, video surveillance, and sound monitoring. The coordinated operation of various interface devices enables unmanned operations for multiple tasks, improving the system's flexibility and adaptability.

[0670] Real-time monitoring and linkage control: This solution provides real-time monitoring and data exchange with video systems, voiceprint monitoring devices, and primary and secondary equipment monitoring systems. By monitoring equipment status and environmental data, it enables intelligent linkage control, enabling rapid response to abnormal situations and improving system security and reliability.

[0671] Data Analysis and Report Generation: This solution uses an intelligent analysis host to intelligently analyze collected data and generate patrol results and unmanned operation reports. This data analysis and report generation capability enables the system to provide more accurate and detailed operational results, facilitating decision-making and optimizing operational processes.

[0672] Compared to other solutions on the market, this solution offers significant advantages in system integration, intelligent analysis capabilities, multi-functional support, real-time monitoring and coordinated control, data analysis, and report generation. These advantages make the system more efficient, flexible, and intelligent, making it suitable for a variety of unmanned operation scenarios, improving operational efficiency and data utilization.

[0673] Example 12

[0674] This embodiment provides an independent microgrid hierarchical control system. Current microgrid control solutions have the following drawbacks:

[0675] 1. Lack of hierarchical control strategy: Current solutions usually lack hierarchical control strategy and cannot achieve coordinated control and optimized scheduling of various levels of the microgrid system.

[0676] 2. Insufficient communication and collaborative performance: Existing solutions have certain limitations in distributed control and communication, and cannot achieve efficient collaborative control and data interaction.

[0677] 3. Lack of flexibility and scalability: The architecture and design of some solutions are not flexible and scalable enough to adapt to microgrid systems of different sizes and needs.

[0678] This solution aims to address the shortcomings of existing microgrid control solutions and provide a hierarchical control model for independent microgrids. This model uses a hierarchical control strategy to achieve coordinated control and optimized scheduling at all levels of the microgrid system, thereby improving the system's flexibility, reliability, and cost-effectiveness.

[0679] The independent microgrid hierarchical control mode of this solution includes the following main components / parts, and the coordinated control of the microgrid system is achieved through the interaction between them:

[0680] a) Energy Management: The energy management layer is the system's top-level control layer, responsible for monitoring and managing the microgrid's energy supply and demand. Its primary functions include energy data collection, demand forecasting, energy planning, and scheduling strategy development. The energy management layer analyzes real-time load demand, power market conditions, and available energy resources to generate energy scheduling instructions to meet the system's power needs and economic requirements.

[0681] b) Control Layer: Located in the middle layer, the control layer serves as a bridge between the energy management layer and the execution layer. Its primary task is to interpret instructions from the energy management layer and transmit corresponding control instructions to the execution layer. Advanced control algorithms and optimization strategies are employed within the control layer to coordinate and optimize the energy system. The control layer is also responsible for monitoring system operating status, fault detection, and fault-tolerant control to ensure safe and reliable system operation.

[0682] c) Execution Layer: Located at the bottom layer, the execution layer is responsible for the actual energy supply and regulation. This layer includes various energy generation equipment, energy storage systems, and energy conversion devices. Following instructions from the control layer, the execution layer actually performs energy transmission and regulation operations to meet the needs and optimization goals of the energy management layer. The execution layer is also responsible for real-time monitoring of equipment operating status, energy quality, and energy supply reliability, and feeding this information back to the control layer for adjustment and optimization.

[0683] The connection / logical relationship and working principle between the above components / parts:

[0684] a) Energy Management and Control Layer: The energy management layer provides the control layer with real-time energy demand information and optimization targets, such as load demand and power generation targets. The control layer formulates scheduling strategies based on this information and passes control instructions to the execution layer.

[0685] b) Control layer and execution layer: The control layer transmits control instructions to the execution layer, including power generation and energy storage operations. The execution layer actually performs energy transmission and regulation operations according to these instructions to meet the needs of the energy management layer.

[0686] c) Energy management layer and execution layer: The energy management layer monitors the operating status and energy supply of the execution layer, and adjusts the energy scheduling strategy and control instructions in real time to adapt to the actual operating conditions and optimize system performance.

[0687] The entire system operates by achieving coordinated control and optimized scheduling of the microgrid system through information exchange and control command transmission between different layers. The energy management layer, as the top-level control layer, is responsible for monitoring the system's energy demand and market conditions and formulating scheduling strategies. The control layer, as the middle layer, interprets the energy management layer's instructions into specific control commands and passes them to the execution layer. The execution layer, as the bottom layer, actually performs energy transmission and regulation operations based on the control layer's instructions to meet the energy management layer's needs. This hierarchical control approach enables coordinated control and optimized scheduling across all levels of the system.

[0688] Preferred:

[0689] As the preferred execution layer algorithm, AI-based reinforcement learning algorithms, such as deep reinforcement learning algorithms, can be considered. These algorithms, through training and learning within independent microgrid systems, can autonomously learn the optimal control strategy based on real-time system status and environmental information, thereby achieving system optimization and performance improvement.

[0690] Specifically, the Deep Q-Network (DQN) algorithm can be used as an example. The DQN algorithm combines deep neural networks with reinforcement learning methods to learn optimal action strategies in a discrete action space. In a standalone microgrid system, the various components and states of the microgrid can be used as input, and a suitable state representation can be designed. This state representation is then fed into a deep neural network for training. The neural network outputs a Q value for each possible action, and then selects the action based on a specific strategy.

[0691] The algorithm's workflow is as follows:

[0692] 1. State representation: Design an appropriate state representation method to encode the information of each component, load demand, energy supply, etc. of the microgrid system into numerical representation.

[0693] 2. Neural Network Construction: Build a deep neural network as an estimator of the Q-value function. The input of the neural network is the state representation, and the output is the Q-value of each possible action.

[0694] 3. Initialization: Initialize the neural network parameters.

[0695] 4. Data collection: Through interaction with the actual microgrid system, data is collected, including current status, actions taken, rewards, and other information.

[0696] 5. Experience replay: The collected data is stored in the experience replay buffer for use in subsequent training processes.

[0697] 6. Neural network training: Randomly sample a batch of data from the experience replay buffer to update the parameters of the neural network to approximate the Q-value function.

[0698] 7. Action selection: Based on the current state and the trained neural network, the best action is selected for controlling the microgrid system.

[0699] 8. Real-time control: Apply selected actions to the independent microgrid system to adjust the supply and transmission of energy to achieve optimized control.

[0700] By using deep reinforcement learning algorithms, the system can autonomously learn the best control strategy based on the real-time environment and system status, and make optimization adjustments to achieve the goal of improving the performance and energy utilization efficiency of the independent microgrid system.

[0701] The advantages of this algorithm include:

[0702] 1. Autonomous learning capability: The algorithm can autonomously learn the optimal control strategy based on the actual environment and system status, reducing dependence on manually set rules.

[0703] 2. Strong adaptability: The algorithm can be adjusted and optimized according to different environmental and system conditions and has a certain degree of adaptability.

[0704] 3. Efficiency: Deep reinforcement learning algorithms are highly parallelizable and can effectively process large-scale state and action spaces, improving computational efficiency.

[0705] By using this optimization algorithm, we can achieve a more intelligent, adaptive and efficient independent microgrid hierarchical control mode, improving the system performance and energy efficiency.

[0706] The optimal use of this solution will vary depending on the specific application scenario and requirements. Here are a few examples of possible optimal use cases:

[0707] 1. High-load periods: When the independent microgrid system is in a high-load period with high load demand and low renewable energy output, the solution can achieve coordinated control of different energy sources through an intelligent hierarchical control mode, ensuring continuous power supply and optimizing energy utilization efficiency.

[0708] 2. Periods of high renewable energy output: During periods of high renewable energy output (such as solar and wind energy), this solution can store, convert, or supply excess energy to other areas based on system needs to maximize the utilization of renewable energy and reduce dependence on traditional energy.

[0709] 3. Energy dispatch in emergency situations: In the face of sudden emergencies (such as natural disasters, equipment failures, etc.), this solution can achieve emergency dispatch and supply of system energy through a fast and intelligent hierarchical control mode, ensuring continuous power supply to critical loads and improving the system's robustness and disaster resistance.

[0710] 4. Periods of large energy price fluctuations: During periods of large energy price fluctuations, the solution can perform intelligent scheduling and optimization based on real-time market price information to achieve the most economical and efficient energy distribution and reduce energy costs.

[0711] Under these optimal usage conditions, the independent microgrid hierarchical control mode can give full play to its advantages of intelligence, adaptability and efficiency, provide reliable, stable and economical energy supply, meet the needs of the system, and achieve optimal energy management and utilization efficiency under different circumstances.

[0712] The above describes in detail the preferred embodiments of the present invention. It should be understood that those skilled in the art can make numerous modifications and variations based on the concepts of the present invention without inventive effort. Therefore, any technical solutions that can be derived by those skilled in the art through logical analysis, reasoning, or limited experimentation based on the concepts of the present invention and the prior art should be within the scope of protection defined by the claims.

Claims

1. A submerged arc furnace production and energy system based on new energy power supply, characterized in that: It includes a power transmission and distribution system, a renewable energy power generation system, an energy storage system and an ore-fired furnace production system, wherein the power transmission and distribution system is connected to the renewable energy power generation system, the energy storage system and the ore-fired furnace production system respectively.

2. The submerged arc furnace production and energy system based on renewable energy power supply according to claim 1 is characterized in that: The submerged arc furnace production and energy system also includes an energy control system, which includes: A renewable energy power generation control system, used to control the operation of the renewable energy power generation system; An energy storage control system, used to control the operation of the energy storage system; A submerged arc furnace production control system, used to control the operation of the submerged arc furnace production system; The integrated control system is used to perform integrated control of the ore-fired furnace production and energy system through the power transmission and distribution system, send control instructions to the renewable energy power generation control system and the ore-fired furnace production control system, and receive control feedback; receive dispatch instructions from the energy storage control system and provide feedback to the energy storage control system.

3. The submerged arc furnace production and energy system based on renewable energy power supply according to claim 1 is characterized in that: The submerged arc furnace production and energy system also includes an exhaust gas recycling system, which is connected to the submerged arc furnace production system and the power transmission and distribution system respectively; The energy control system also includes an exhaust gas recycling control system, which is used to control the operation of the exhaust gas recycling system.

4. The submerged arc furnace production and energy system based on renewable energy power supply according to claim 1 is characterized in that: The submerged arc furnace production and energy system also includes an external power grid connected to the power transmission and distribution system; The energy control system also includes a power grid dispatching system, which is used to dispatch energy to an external power grid.

5. A method for controlling a submerged arc furnace production and energy system based on new energy power supply as claimed in any one of claims 1 to 4, characterized in that: The following steps are involved: Establishing a mathematical model for the ore-fired furnace load and renewable energy in the energy system, and obtaining real-time data of the ore-fired furnace load and renewable energy; Constructing a prediction model of the submerged arc furnace load and renewable energy based on historical data, and predicting the load change of the submerged arc furnace load and the output power of renewable energy based on the acquired real-time data; The energy system is coordinated and controlled according to the prediction results of the ore-fired furnace load and renewable energy.

6. A multi-time scale load power forecasting method, characterized in that: The following steps are involved: Obtain historical load data, and divide the historical data into load data of multiple time scales; According to the load data of different time scales, the corresponding prediction algorithm is adopted to construct and train the load prediction model of the corresponding time scale; The real-time load data is loaded into the load forecasting model of the corresponding time scale to obtain the forecast results of the corresponding time scale.

7. A source-grid-load-storage integrated coordinated control method, characterized in that: The following steps are involved: Power prediction steps: Obtain historical data and real-time data of power generation equipment to make power predictions; Load forecasting steps: Obtain historical load data to perform load forecasting Day-ahead power generation planning steps: Based on the predicted load changes of the ore-fired furnace and the output power of renewable energy, the output plan of renewable energy and the charging and discharging plan of the energy storage system for the next day are constructed to form a day-ahead power generation plan; Intraday rolling optimization step: according to the real-time load demand and power generation capacity of the energy system, the day-ahead power generation plan is revised, and the revised day-ahead power generation plan is dynamically adjusted and optimized; Automatic power generation control steps: Control the active power of each generator set in the energy system to achieve real-time balance between power generation output and load demand; Automatic voltage control steps: control the reactive voltage equipment in the energy system to achieve online optimized closed-loop control of voltage; Source-load coordination control step: According to the power generation plan determined by the intraday rolling optimization step, determine and issue power control instructions for each load, renewable energy and energy storage system in the energy system; Stable control step: Stable control is performed on the corresponding equipment according to the power control instruction, and system stability control is performed in an emergency.

8. A centralized control system and a stabilization control system coordinated control system, characterized in that: include: Centralized control module, stable control module and coordinated control module; The centralized control module is used to monitor the operating status and parameters in the energy system and transmit them to the collaborative control module; Receive control instructions issued by the collaborative control module to dispatch and control the energy system; The stability control module is used to monitor parameter changes of the energy system, perform stability analysis, generate corresponding stability control instructions, and transmit them to the collaborative control module; The collaborative control module is used to integrate and analyze the information transmitted by the centralized control module and the stable control module. A comprehensive control strategy is formed, and corresponding control instructions are transmitted to the centralized control module and the stabilization control module to perform coordinated control of the system.

9. A method for optimizing and coordinating the control of a wind-solar-storage station, wherein the wind-solar-storage station includes a wind power generation device, a photovoltaic power generation device and a corresponding energy storage system, characterized in that: The method comprises the following steps: Data acquisition step: acquiring operation data information in the wind-solar storage station; Active power optimization and smoothing steps: Based on the operating data information in the wind and solar storage station, determine whether the power output fluctuations of wind power generation equipment and photovoltaic power generation equipment need to be smoothed. If necessary, calculate the required charging and discharging power based on the charging and discharging capacity of the energy storage system and the current power fluctuations, and control the energy storage system to perform charging and discharging operations based on the charging and discharging power; Active power instruction optimization tracking step: comparing the active power instruction transmitted to the wind-solar power storage station with the actual output of the wind-solar power storage station, so as to determine whether it is necessary to compensate the output of the wind-solar power storage station, and if necessary, calculating the compensation value and adjusting the output of the wind-solar power storage station; The first frequency modulation step is to obtain the frequency deviation of the wind-solar-storage station grid connection point, determine whether frequency modulation control is required, and if necessary, adjust the output power of each device in the wind-solar-storage station.

10. A multi-source adaptive power generation coordinated control method, characterized in that: The following steps are involved: Obtain status data of each power generation equipment in the power grid; The state data of each power generation equipment is centrally trained by using federated learning to obtain a global power generation prediction model; the global power generation prediction model is combined with the corresponding physical model of the power generation equipment to obtain an overall prediction model; According to the real-time status data and optimization objectives of each power generation device, the power generation control strategy and parameters of the overall prediction model are dynamically adjusted, and the control strategy of each power generation device is obtained using the adjusted overall prediction model.

11. A composite allocation method with the goal of optimizing efficiency, characterized in that: The following steps are involved: According to the real-time data in the power system, a composite allocation algorithm is used to select the optimal energy allocation scheme for each power generation equipment and load, wherein the composite allocation algorithm is composed of a combination of multiple optimization strategies; According to the optimal energy allocation plan, corresponding control instructions are generated to control and adjust each power generation equipment and load.

12. A multi-energy emergency machine-grid coordination system, characterized in that: include: Wide-area dynamic synchronous monitoring system for synchronous dynamic monitoring of transient disturbances and faults in energy systems; Rapid collaborative control system, used to quickly respond and coordinate different types of power generation equipment in the energy system. Same control; Grid stability control system, used to stabilize and regulate the grid of the energy system; The energy storage frequency stabilization cooperative control system is used to achieve frequency stabilization and coordinated control of the energy storage system.

13. An automated intelligent power supply network reconstruction method, characterized in that: The following steps are involved: Obtain the status data of the power supply network in the energy system, and perform network topology analysis and fault diagnosis based on the status data; if a power supply network fails, obtain a reconstruction plan for the power supply network based on the preset power supply optimization strategy; The power supply network is topologically reconstructed according to the power supply network reconstruction scheme.

14. A five-line defense-based isolated grid stability control method, characterized in that: The following steps are involved: Monitor whether the energy system has any faults. If a fault occurs, identify the faulty area in the energy system within the first time after the fault occurs, and isolate the faulty area through preset protection elements; Reconstruct the power supply network of the energy system within a second after the fault area is isolated; After a third period of time after the fault area is isolated, the power balance and frequency recovery of the energy system are performed by controlling the output of the power generation equipment in the energy system and adjusting the load; If the frequency of the energy system is within the first unstable range, the frequency of the energy system is controlled by means of low-frequency and low-voltage load shedding and high-frequency machine cutting control; If the frequency of the energy system is within the second unstable interval, the minimum power generation systems are divided into the energy system and each minimum power generation system is started.

15. An independent microgrid hierarchical control system, characterized in that: include: The energy management layer is used to monitor and manage the energy supply and demand of the energy system, generate energy dispatch instructions, and adjust the energy dispatch instructions in real time according to the execution results of the execution layer; The control layer is used to formulate corresponding dispatch strategies according to energy dispatch instructions and generate control instructions; The execution layer is used to regulate the energy of the equipment in the energy system according to the control instructions transmitted by the control layer.

16. An intelligent unmanned operation system, characterized in that: include: An unmanned operation host, an intelligent analysis host and a variety of automatic data collection devices, wherein the unmanned operation host is connected to the intelligent analysis host and the various automatic data collection devices respectively; The unmanned operation host is used to issue control instructions to each automatic data collection device and receive data transmitted by each automatic data collection device; The intelligent analysis host is used to analyze the data collected by the unmanned operation host to form a data analysis conclusion. fruit.

Images